Agent Rynku - Warsaw Stock Exchange (GPW) data for your agent

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The readOnlyHint annotation already establishes this is a safe read operation, and the description does not contradict it. The description adds the analysis scope (AI value chain exposure) but discloses no behavioral details such as data dependencies, whether a portfolio must exist first, or what 'dziura' (gap) means operationally. Given the annotation carries the safety burden, a 3 is appropriate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single dense sentence with zero filler. The core promise is front-loaded ('rozkład portfela') with the value proposition in the second clause. Every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter read-only tool, the description conveys the core purpose adequately and hints at the deliverable (exposure and gap locations). However, with no output schema, it does not describe the result format or how the breakdown is presented, which is a minor gap given the tool's simplicity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the input schema is vacuously complete and there is nothing for the description to add about parameter meaning. Per the baseline for parameterless tools, a 4 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific deliverable: a portfolio breakdown across AI value chain links, identifying exposure and gaps. This differentiates it from generic portfolio tools like get_portfolio_analytics or get_concentration_risk. It lacks an explicit imperative verb, but the analytic intent is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives, and the term 'thesis' in the name is never explained. There is no mention of prerequisites, complementary tools, or conditions that would make another sibling more appropriate. An agent must infer usage entirely from the name and description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With readOnlyHint=true, the safety profile is covered, but the description adds no behavioral detail such as what output is produced, how outcomes are judged, or how externalId and dateIso interact. The vague phrase 'co wyszło, a co nie' is not a concrete behavioral contract.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is short and free of filler, but it is under-specified and colloquial rather than a clean structured statement. It earns its place but does not front-load a precise action or object.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with four optional parameters, no output schema, and no usage guidance, a single vague sentence is insufficient. The agent is left without information on return values, parameter selection, or when this tool is appropriate, and the dateIso contradiction adds confusion.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3, but the description actively conflicts with the schema: it says 'single transaction' while dateIso says 'analyze all trades on that day.' It adds no meaning beyond the schema and misleads about scope.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Rozliczenie pojedynczej transakcji: co wyszło, a co nie' indicates the tool evaluates a trade outcome, but it is a noun phrase rather than a clear verb+resource statement and does not distinguish it from siblings like get_realized_pnl or get_evaluation_outcomes. It also narrows scope to a 'single transaction' even though the dateIso parameter explicitly supports analyzing all trades on a day.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is given about when to use this tool versus the many sibling tools; there is no mention of alternatives, exclusions, or typical use cases. The only implied context is 'single transaction,' which is contradicted by the dateIso parameter.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

readOnlyHint=true already signals a safe read operation, and the description adds no behavioral context beyond that: no mention of what inputs drive the calculation, what the result represents, or any caveats about defaults. The description contributes nothing beyond the annotation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single short phrase, but this is under-specification rather than conciseness. There is no front-loaded verb sentence and no structured content that earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description should at least indicate what the calculation returns, but it says nothing about the result or how to interpret profitability. For a 3-parameter financial calculation tool, this is incomplete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% with strong inline explanations (par-value formula, default chain for redemptionPricePct), so the schema carries the full meaning and the baseline of 3 applies. The description itself adds no parameter-level value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The Polish description ('Calculation of profitability of early redemption of bonds') identifies the resource (bonds) and the action (profitability calculation), but it is a noun phrase that mostly restates the tool name. It never explains what 'profitability' is measured against, and the non-English phrasing reduces clarity for an AI agent.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no guidance on when to use this tool, what prerequisites exist (e.g., knowing the bond series and holdings value), or when a sibling tool would be more appropriate. A single terse phrase provides no decision support.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare destructiveHint=true and readOnlyHint=false, so the destructive nature is known. The description adds no further behavioral context (e.g., irreversibility, impact on related data, or whether any note field is affected) beyond what the annotations provide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence with no wasted words or redundant detail. It front-loads the core action, though it is brief to the point of being sparse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive operation, it would be helpful to note consequences (e.g., whether cancellation is permanent, if there is any confirmation step). The description gives no such context, and the lack of an output schema means no return-value guidance. It is minimally adequate but incomplete for a mutation tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with both 'eventId' and 'reason' described in the input schema. The description itself does not add any extra meaning about parameters, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Odwołanie śledzonego zdarzenia' (cancellation of a tracked event) clearly states a specific action (cancel) and resource (tracked event). It is unambiguous but does not differentiate it from sibling tools like 'resolve_priced_event_now' or 'update_priced_event'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives, no context about prerequisites (e.g., event must be tracked first) or when cancellation is appropriate. The description only states what it does, not when or why.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotation only states readOnlyHint=false, so the description carries the burden of explaining the mutation. It says the request can be claimed or released back to the queue, which adds a little context, but does not disclose ownership effects, release constraints, idempotency, or what happens after claiming.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single short sentence with no filler, and it front-loads the core action. However, it is perhaps too terse for a tool with four parameters and non-trivial release semantics.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and minimal annotations, the description should explain more about the claim/release workflow, such as what it means to hold a request, whether release requires an owner, and what the response indicates. The schema covers parameters, but the overall operation is only partially described.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so parameters are already well documented, including the unusual pomiarDzis behavior. The tool description itself adds no parameter-level meaning, which lands at the baseline 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a clear action: taking a request into work or returning it to the queue, which maps well to the tool name claim_feature_request. It covers both claim and release semantics, but is written in Polish and does not explicitly distinguish itself from siblings like submit_feature_request or list_feature_requests.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided about when to use this tool versus alternatives, nor are any exclusions or prerequisites mentioned. The description implies the tool is for claiming or releasing feature requests, but an agent must infer the appropriate context from the name and schema.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotation readOnlyHint=true is consistent with the described ranking behavior, so there is no contradiction. The description adds the sorting criterion and scope, but it does not disclose metric definitions, output format, or how includeWatchlist affects behavior beyond the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is one front-loaded sentence with no redundant words or irrelevant detail. It is concise and easy to parse, even though it sacrifices some contextual depth.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only tool with two optional parameters, the description is nearly sufficient, but it does not describe the shape of the returned ranking or the risk/reward measure used. The lack of usage alternatives also leaves some context missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so both limit and includeWatchlist are already documented in the input schema. The tool description adds no parameter-level meaning, but it is not required to compensate because the schema carries the full burden.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies a ranking operation over positions and watchlist items using a profit-to-risk criterion, so the resource and output type are evident. However, it does not explicitly differentiate itself from related siblings like get_stock_rankings or rank_thematic.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description offers no guidance on when to use this tool instead of analysis or ranking alternatives, and it states no preconditions or exclusions. Usage context is only implied by the name and the single sentence.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The readOnlyHint annotation already communicates that this is a read-only operation, and the description adds no additional behavioral context such as output shape, side effects, rate limits, or plan restrictions. It does not contradict the annotation, but it contributes nothing beyond it.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded phrase with no filler or repetition. It is economical, though its brevity leaves some contextual gaps.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With complete parameter schema and a read-only annotation, the tool is minimally invokable, but the description alone does not provide usage context, alternatives, or output expectations. It is adequate but not complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema fully documents both symbols and metrics, including defaults and plan-based behavior. The description's mention of 'companies' only loosely maps to the 'symbols' parameter and adds no technical meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The Polish description 'Porównanie kilku spółek obok siebie' clearly conveys side-by-side comparison of multiple companies, naming the resource and the action. However, it does not explicitly distinguish this from sibling tools like compare_portfolio_risk_reward or get_company_analysis.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is given about when to choose this tool over its alternatives, nor are any exclusions or prerequisites stated. The description only says what the tool does, not when it should be used.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only provide readOnlyHint=false, so the description itself must disclose side effects. 'Utworzenie' correctly indicates a write operation, and 'ma pilnować warunku za Ciebie' hints at ongoing rule monitoring. However, the description does not state that the rule is persisted, what happens after creation, whether creation can fail, or what the response contains; the schema-level notes about blocked auto_execute and stale quotes are useful but parameter-scoped.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The main description is a single, front-loaded sentence that identifies the action and resource with minimal waste. It is concise, though it misses an opportunity to add a sentence about usage or behavior; the heavier explanatory burden is correctly delegated to the input schema.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of the 5-parameter nested schema, the detailed schema descriptions carry most of the contextual weight. However, there is no output schema and the description does not explain what the tool returns, whether creation is idempotent, or whether any authorization or persistence semantics apply, leaving some gaps for an agent invoking the tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3 even though the main tool description adds no parameter semantics. The schema itself provides very detailed and helpful descriptions for trigger and action, so the agent can construct valid payloads, but the tool description itself does not contribute additional parameter meaning.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Utworzenie' (create) and the resource 'reguły decyzyjnej' (decision rule), adding the high-level purpose of watching a condition. It is specific enough to distinguish creation from listing, updating, or deleting decision rules, though it does not explicitly name a sibling or contrast with another tool.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives such as update_decision_rule, delete_decision_rule, or list_decision_rules. The only usage-related guidance appears inside the trigger parameter description, which discusses choosing trigger kinds, but that is parameter-level rather than tool-selection guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds no behavioral context beyond what annotations already declare (destructiveHint=true). It does not mention irreversibility, side effects, or any requirements, missing the opportunity to add value beyond the structured data.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise (one phrase), which is efficient, but it lacks structure and does not front-load any additional useful information. It is not verbose but also not informative beyond the basic purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple delete operation with one parameter and no output schema, the description is minimally adequate. However, it does not mention what happens on success or failure, and the destructive nature is only implied by annotations. The description could be more complete without being verbose.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the description does not add any parameter details beyond what the schema already provides. The description does not mention the ruleId parameter at all, so it meets the baseline but adds no extra semantics.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states the specific action (delete) and resource (decision rule), which clearly differentiates it from create/update siblings. It is not a tautology because it names the resource explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives such as update_decision_rule or list_decision_rules. There are no conditions, prerequisites, or exclusions stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The readOnlyHint annotation already establishes that this is a safe read operation. The description adds a modest behavioral cue: the tool does not return every fallen stock, but filters for companies whose fundamentals still hold. However, it does not explain thresholds, the cost of universe scans, or result behavior, so the added transparency is limited.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single focused sentence with no filler, and the core idea is front-loaded. It loses one point because the terseness omits usage and behavioral context that would help an agent select and invoke the tool confidently.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the read-only annotation, zero required parameters, and exhaustive parameter descriptions, this is minimally viable: an agent can infer the tool's purpose and call it sensibly. However, there is no output schema and the description does not mention return shape, limitations, pricing, or how it differs from sibling screening tools, leaving some ambiguity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and the parameter descriptions—especially for anchor, scope, and minDrawdownPct—already carry substantial semantic detail. The tool description itself adds no parameter-level meaning, so the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The Polish description, 'Spółki, które mocno spadły, ale fundamenty trzymają', clearly conveys that this tool finds companies that have fallen sharply while retaining sound fundamentals. It implicitly distinguishes itself from sibling tools like find_overheat_candidates, but it is a noun phrase rather than an explicit verb+resource statement and does not mention the returned shape.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided about when to use this tool versus alternatives such as find_overheat_candidates, find_opportunities, or get_top_opportunities. There are no exclusions, prerequisites, or routing conditions; the intended use is only implied by the tool name and the one-line description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, which covers safety. The description adds no behavioral context beyond that—no mention of result format, ordering, or side effects. Parameter descriptions in the schema provide some nuance, but the tool-level description offers nothing new.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, brief sentence, but it is under-specified. Conciseness should pair with substance; here it's shorter than needed to be helpful. It doesn't front-load any critical distinguishing information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With 7 optional parameters carrying nuanced behaviors (e.g., forecastFreshnessDays, maxPriceSessionsMissed), no output schema, and many sibling tools, the description is inadequate. The agent lacks context on what this tool returns, how it fits with alternatives, and what edge cases matter.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so every parameter has a description. The tool description itself adds no parameter information beyond what the schema provides. Baseline of 3 is appropriate since the schema handles documentation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a verb ('search') and a resource ('opportunities'), but it's vague about what kind of opportunities. It doesn't distinguish from siblings like find_dip_candidates or find_overheat_candidates. The phrase 'according to given criteria' hints at filtering but doesn't specify the domain or differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus alternatives. There is no mention of exclusions, preferred contexts, or trade-offs. With many opportunity-related sibling tools, this is a significant gap that leaves the agent to guess which one fits.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotation readOnlyHint=true already signals this is a read-only operation, so the description does not need to restate that. However, it adds no behavioral context: it doesn't mention whether the scan is expensive, what the default scope/universe is, how results are returned, or any side effects. The schema comments cover some of this (e.g., 'universe' being expensive), but the description itself carries no extra behavioral information.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely short (one clause), which might seem concise, but it fails to front-load the purpose. Instead of stating 'Find overheat candidates' it offers a vague characterization of the output. The single sentence does not earn its place because it communicates almost nothing actionable.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 6 optional parameters and no output schema, the description is severely incomplete. It does not clarify what the tool returns (list of symbols? scores?), what the default behavior is (e.g., scope='both'), or how to interpret the results. An agent cannot reliably call this tool based on the description alone. The lack of any output format or usage context makes it inadequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and the parameter descriptions in the schema are quite detailed (e.g., maxScore explains its role and PRO-only nature). The tool description adds no parameter-related meaning, but since the schema already documents parameters thoroughly, this is acceptable. The baseline of 3 applies because the description does not actively mislead or conflict with the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description is a noun phrase ('Companies that have grown faster than results justify') rather than a statement of the tool's action. It does not explicitly state a verb like 'find', 'list', or 'scan', nor does it name the resource it operates on. It conveys the output criteria but not the operation itself, making it hard for an agent to know what the tool actually does.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus its siblings (e.g., find_dip_candidates, find_opportunities, find_tlh_opportunities). The description does not mention any conditions, prerequisites, or scenarios where this tool is preferred. An agent has no basis for selecting it among the many screening tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description is consistent with readOnlyHint=true and adds a useful domain constraint: losses must be tax-deductible in the current year. It does not, however, reveal anything about return format, replacement suggestions, or sorting behavior beyond what the input schema already covers.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single terse sentence with no fluff, so it is concise. However, it is under-specified as a standalone definition and lacks structure or clarification, making it less useful than a well-organized purpose-and-usage statement.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and strong reliance on the tool name, the description is incomplete: it does not describe what an agent should expect in the response, what 'tax deductible' entails, or how this tool relates to its many siblings. The safe read-only annotation and detailed parameter schema partially compensate, but the overall context is thin.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline applies. The description itself adds no parameter-specific meaning, but the schema already documents maxResults cap/sorting, minLossPLN threshold, and sameSector replacement behavior, so the description does not need to compensate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the tool's output: positions with a loss that can be deducted from tax this year. This is a specific, meaningful purpose rather than a tautology. However, it lacks an explicit verb and does not distinguish itself from sibling find_* tools like find_opportunities or find_dip_candidates.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance about when to use this tool instead of alternatives such as find_opportunities, find_dip_candidates, or get_top_opportunities. The tax-loss context is implied by the name and description, but no explicit when-to-use, prerequisites, or exclusions are provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotation already declares readOnlyHint=true, and the description adds little behavioral context beyond 'recent events.' It does not state ordering, pagination behavior, response format, or what counts as an event, though the read-only safety profile is covered by the annotation. No contradiction exists.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single short sentence with no filler, making it easy to parse. It is concise, though it sacrifices useful context for brevity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 3 optional filtering parameters, no output schema, and multiple similarly named feed/event tools, the description is too thin to fully orient an agent. It does not indicate what an activity event looks like, how results are ordered, or why this feed differs from related tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

All three parameters are fully described in the input schema, including allowed values and defaults. The tool description itself adds no parameter-level meaning, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description, 'Recent events on your account,' names a clear resource (the account activity feed) and implies retrieval, matching the tool name. It is understandable but does not differentiate this feed from nearby siblings such as get_alerts, get_transaction_history, or get_news_history.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool rather than get_alerts, get_news_history, get_transaction_history, or list_webhook_events. The description does not mention filtering, typical use cases, or any exclusion criteria.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already provide readOnlyHint=true, so the read-only nature is covered. The description adds the output dimension of sent versus failed counts, but it does not disclose aggregation behavior, scope (e.g., user-specific vs. platform-wide), or any limits beyond the schema. There is no contradiction with the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no filler words. It communicates the core purpose immediately. However, it is terse to the point of omitting useful clarifying context, so it does not earn a perfect score.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with two optional parameters, a fully described schema, and a read-only annotation, the description is minimally sufficient. The main gap is ambiguity about whether the statistics are scoped to the current user or system-wide, which matters given the sibling tool get_my_alert_performance. There is also no output schema to clarify the exact response structure, but the description's mention of counts partially addresses this.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema covers both parameters with full descriptions, including defaults and allowed values, so the baseline of 3 applies. The description does not add any extra parameter semantics, but the schema already carries the necessary information about channel filtering and lookback window.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states that the tool reports alert delivery statistics, specifically counts of sent and failed deliveries. It identifies the resource ('alert delivery') and the output ('how many went, how many failed'), making the core purpose understandable. It does not explicitly differentiate it from sibling tools like get_my_alert_performance, but the resource and focus are reasonably distinct.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives such as get_my_alert_performance, list_webhook_events, or get_alerts. It does not mention exclusions, prerequisites, or typical scenarios. An agent must infer usage entirely from the tool name and the parameter schema.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only provide readOnlyHint, so the description carries the full burden of behavioral disclosure. It does not mention the database-level filtering behavior for the universe parameter (which scans past US alerts on a measured account), the exclusion of alerts with undetermined markets, or any pagination caveats. The description adds no behavioral context beyond the tool's basic purpose.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, very concise and front-loaded with the core purpose. It avoids fluff and is easy to parse. However, it is so brief that it omits key information about additional filters, which slightly reduces its usefulness despite the clean structure.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 5 optional parameters and no output schema, the description is minimal. It does not mention the universe filtering caveats, default limits, or any behavioral nuances that an agent might need to know for correct invocation. The description is insufficient for a tool with this complexity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description mentions filters for company and classification, which map to the symbol and classification parameters, but it does not add any new meaning beyond what the schema already provides. It does not explain the universe filter's nuanced behavior, so it stays at the baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states that the tool returns alerts for the current user and supports filtering by company and classification. This provides a specific verb, resource, and scope, distinguishing it from generic 'get' tools. However, it does not explicitly differentiate from any sibling tools, though none appear to be direct alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no guidance on when to use this tool versus alternatives. It does not mention any exclusions, prerequisites, or conditions that would help an agent decide between this and other alert-related tools like get_alert_delivery_stats or get_my_alert_performance. There is no 'when not to use' information.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotation readOnlyHint=true already indicates a safe read operation. The description adds minimal behavioral context by mentioning that signals come with attached evidence in the data, which implies a structured output. However, it does not disclose pagination, limits, or response format, so it adds only a small amount beyond the annotation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence that is front-loaded with the core purpose. There is no wasted wording, and it is appropriately sized for a straightforward read-only tool. However, it is very terse and could benefit from a tiny bit more context without becoming verbose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 3 optional parameters and no output schema, the description is insufficient for an agent to understand when to select it among many similar siblings. It lacks usage context, return format details, and any mention of portfolio versus single-asset handling. The evidence clause hints at output structure but does not provide enough to confidently invoke the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents each parameter thoroughly. The description does not add any extra meaning beyond what the schema provides, but the baseline of 3 applies when the schema handles parameter details.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: detecting opportunities and risks for a company, each with data-backed evidence. It names a specific resource (asset signals) and a verb (detect), which distinguishes it from vague tool names. However, it does not explicitly differentiate from siblings like find_opportunities or get_risk_dashboard, so it lacks a clear contrast.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It does not mention exclusions, prerequisites, or typical scenarios. The parameters hint at portfolio vs single-asset usage, but the description itself gives no explicit usage context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The readOnlyHint annotation already marks it safe, and the description adds key behavioral context beyond that: the tool is currently unavailable and returns only a postponement notice rather than an actual order book. This is valuable, non-obvious disclosure. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single front-loaded sentence with no filler. It promptly states the resource and the crucial caveat, though it could arguably provide a bit more structured context like an availability note or alternative reference.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple, one-parameter, read-only placeholder tool, the description is adequately complete: it says what the tool would provide, that it is currently unavailable, and what it returns instead. The lack of an output schema is partially mitigated by the explicit mention of the postponement notice.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, and the single parameter 'series' is already documented with an example. The tool description adds no further meaning about the parameter, so the schema carries the full burden; baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the resource ('Arkusz zleceń dla obligacji' – bond order book) and states the current behavior ('zwraca informację o odroczeniu' – returns postponement notice). It is specific enough to distinguish from the many other get_* tools, though it lacks an explicit verb like 'get' or 'retrieve'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is given on when to call this tool versus alternatives. The description only notes that it is currently unavailable, but does not suggest an alternative tool or any context in which this stub should be used.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations include readOnlyHint=true, so the description doesn't need to state safety. It adds context about filtering by issuer, margin, and maturity, which is useful. However, it doesn't disclose behaviors like defaulting to excluding matured series (though schema says default false) or that issuer matching is case-insensitive (schema covers that). The description adds minimal context beyond schema and annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, concise with no fluff. It front-loads the key criteria (issuer, margin, maturity). It's efficient, though 'z Catalyst' is redundant as the tool name implies it.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's complexity (8 parameters, no output schema), the description is insufficiently complete. It doesn't explain that results are filtered by sector or equity symbol, nor does it clarify that margin filter only applies to floating rate bonds. However, since there is no output schema and no nested objects, the tool might return a simple list, and the description provides a basic picture of what it returns.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is high at 88%, so the schema already documents most parameters. The description mentions 'marży' (margin) and 'termin wykupu' (maturity), which maps to marginPctMin and maturityWithinDays, but doesn't add new meaning beyond what schema provides for those. Overall, the description adds little value beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool finds bond series from Catalyst by issuer, margin, and maturity date. However, it doesn't differentiate from siblings like get_bond_orderbook, which also deals with bonds, though get_bond_orderbook is likely about orders rather than series.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for filtering bond series, but doesn't explicitly state when to use this vs alternatives like get_bond_orderbook or get_company_analysis. It also doesn't mention that all parameters are optional or that the tool returns series based on filters, which is implicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description adds no behavioral context beyond what the readOnlyHint annotation already provides. It does not mention side effects, authentication requirements, or any special behavior. Since annotations already cover read-only, the description contributes minimal additional transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence in Polish, front-loaded with the core purpose. It is efficient with no filler or redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is insufficient for a tool with no output schema. It states 'statistics' but does not specify which statistics are returned, the format, or any details about the return value. An agent calling this tool would not know what to expect in the response, leaving a significant gap in context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, and the input schema is fully covered. The description does not need to explain parameter semantics. The baseline of 4 applies because there is nothing to compensate for; no parameters exist to be described.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a clear purpose: providing statistics about a data extraction pipeline from reports. The verb 'get' and resource 'pipeline stats' are explicit. It does not differentiate from sibling tools like get_pipeline_health, but the name itself is specific enough to indicate what it covers.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. There are several similar get_* tools (e.g., get_pipeline_health, get_alert_delivery_stats), but the description gives no context for selecting this one. The agent is left to infer from the name alone.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The readOnlyHint annotation already covers safety, and the description adds that only a preview is returned while full content is PRO-gated, which is useful and non-contradictory. However, it does not disclose what the preview contains or whether PRO is required even to call the tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences with no filler. The core purpose is front-loaded and the PRO limitation is relevant, concise, and clearly stated.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a one-parameter read-only tool, the description is minimally adequate, but it leaves ambiguity about what the returned preview will include and how this differs from many similar sibling get_* tools. No output schema exists to compensate for this vagueness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% and the description does not explain the symbol parameter at all. While 'symbol' is somewhat self-explanatory, the description adds no meaning about expected format, such as ticker vs ISIN, or any constraints.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the resource: a preview of a company's fundamental analysis, and adds the PRO limitation. It is understandable, though it uses a noun ('Podgląd') rather than an imperative verb and does not differentiate itself from sibling analysis tools like get_company_dossier or get_drivers.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance about when to use this tool versus alternatives, no exclusions, and no mention of related sibling tools. The PRO note implies a preview-only use case, but that is implicit rather than actionable routing guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The readOnlyHint annotation already covers safety, and the description adds meaningful behavioral context by specifying the type of information returned: persistent advantages, weaknesses, open risks, confirmed patterns, and business context. It does not discuss output format or staleness, but for a read-only getter this is reasonably transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single compact sentence with a colon-separated list, front-loading the core concept and avoiding filler. Every phrase contributes meaning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple two-parameter schema, the read-only annotation, and the absence of an output schema, the description provides enough contextual coverage: it names the kind of content an agent will receive. It could be more complete with an explicit output shape or an example, but the tool is simple enough that this is a minor gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description indirectly gives meaning to perCategoryLimit by listing the categories it applies to, and the schema already documents its default. However, the required symbol parameter has no schema description and the description does not clarify it beyond the tool name, so the parameter semantics are only partially compensated.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly conveys that this tool provides a company's decision-focused memory: durable strengths, weaknesses, open risks, confirmed patterns, and business context. It implies the resource and content, though it lacks an explicit verb such as 'returns' or 'retrieves' and does not distinguish itself from sibling tools like get_company_analysis.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied rather than explicit: an agent would use this when it needs persistent, qualitative company context rather than real-time signals. However, the description names no alternatives and gives no when-not-to-use guidance, leaving sibling differentiation to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations provide readOnlyHint=true and the description does not contradict that. However, the description adds no behavioral context beyond the core purpose: it does not mention output format, return shape, threshold defaults, or how the three axes are reported. With no output schema, this gap is noticeable.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, short, front-loaded sentence with no filler. It loses slight points because the phrasing is terse and grammatically loose, and it omits any structural cues such as examples or scoping details.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no output schema, the description only explains the question being answered, not what the caller receives. It does not mention risk levels, percentages, threshold behavior, or the effect of the optional parameters, so an agent is left without enough context to fully interpret the result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline of 3 applies. The description does not mention the optional thresholds or topDriversPerSymbol parameters, but the schema already documents them adequately, so no significant added meaning is needed or provided.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The Polish description 'Ile portfela stoi na jednej spółce, sektorze i rynku' clearly communicates that the tool measures portfolio concentration across a single company, sector, and market. It names the resource and scope, but lacks an explicit verb like 'calculates' or 'returns' and does not explicitly distinguish it from sibling analytics tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives such as get_risk_dashboard or get_portfolio_analytics. The description simply states what the tool reports, leaving tool selection entirely to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The readOnlyHint annotation already signals a safe read, and the description adds scope context: only upcoming earnings conferences for followed companies. It does not disclose any additional behavioral traits such as authentication, default window behavior, or response shape, but with the annotation present this is acceptable.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise phrase with no filler or repetition. It is appropriately sized for a simple getter, though it lacks the structured detail that could make the tool stand out from siblings.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a low-complexity read tool with two optional documented parameters and readOnlyHint, the description conveys the core return set but leaves some ambiguity about what a 'reminder' includes and whether the followed-company scope is the user's watchlist. It is minimally complete but not rich.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema covers both optional parameters with clear descriptions: symbol is a canonicalized single-symbol filter and daysAhead has a default/max. The description adds no parameter meaning, so it earns the baseline score for high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The Polish description translates to 'Upcoming earnings conferences of companies you follow,' which identifies the returned resource and its personalized scope. It is clear but uses a noun phrase rather than an explicit verb such as 'returns' or 'lists,' so it stops short of the top rating.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no guidance about when to choose this tool over siblings such as get_conference_summary or get_earnings_calendar. It implies usage for tracking companies, but provides no exclusions or alternative routing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark readOnlyHint=true. The description adds that the summary includes management quotes, forecasts, and warning signals, which is useful but not a deep behavioral disclosure. It doesn't describe additional behavioral traits beyond what the schema and annotations provide.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single front-loaded sentence with no extra words. Every word contributes to the core concept, making it highly efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only tool with fully documented parameters, the description is largely sufficient: it names the resource and its content. Minor gaps include lack of usage guidance and a language mismatch (Polish description vs English tool name/schema), but no output schema is needed given the content description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%: symbol is required and canonicalized, limit has a default of 1 and newest-first ordering, conferenceDate is optional for a specific past conference. The description itself adds no parameter-level meaning, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the resource (results conference summary) and its contents (management quotes, forecasts, warning signals). It uses a noun phrase rather than an explicit verb, and doesn't explicitly differentiate from sibling get_ tools, but the content detail makes the purpose unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool vs alternatives. The description is purely descriptive and doesn't mention conditions, exclusions, or alternative tools like get_conference_reminders.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, so the description does not need to state read-only behavior. It adds value by specifying that it provides correlation and valuation difference, which is behavioral context beyond the annotation. However, it does not disclose any additional limitations or edge cases.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence that immediately states the purpose and the key output (counterparts, correlation, valuation difference). It is front-loaded with the core functionality and contains no redundant words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only tool with two parameters and no nested objects, the description adequately explains the output and the intended use case. It does not mention pagination or limits, but given the likely small response size for a peer set and the readOnlyHint annotation, the coverage is sufficient. Absence of an output schema is partially compensated by the description's mention of correlation and valuation difference.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, with both parameters having clear descriptions (symbol: 'Either side of the PL<->US mapping; server canonicalizes'; market: 'Optional peer market filter'). The description does not add further parameter-specific guidance beyond what the schema already provides, so a baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states what the tool does: it returns company counterparts on the other market with correlation and valuation difference, specifically for comparing GPW with the US market. This is a specific verb+resource+scope, and it distinguishes itself from other get_* tools by focusing on cross-market peer comparison.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives a clear use case ('do porównania GPW z USA'), but it does not explicitly state when to use this tool vs. alternatives or when not to use it. It implies usage for cross-market comparison but lacks exclusions or references to sibling tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The readOnlyHint annotation already covers the safety profile, and the description does not contradict it. The description adds the content scope (changes in portfolio and watchlist) but provides no extra behavioral context such as output format, freshness, or limits.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single front-loaded sentence with no filler. It immediately communicates the time window and subject matter, which is appropriately concise for a parameterless tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter, read-only briefing tool, the description conveys the core intent and scope sufficiently. It does not specify the exact structure of the briefing, but this is a minor gap given the simple input schema and read-only annotation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters, so the schema covers all parameter semantics by definition; the baseline of 4 applies. The description's mention of portfolio and watchlist reinforces that the tool relies on the user's pre-existing context.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly names the resource: a daily briefing ('Odprawa na dziś') that reports changes in the user's portfolio and watchlist. This goes beyond a tautology, but it does not explicitly distinguish itself from sibling getters like get_activity_feed or get_portfolio_context.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'na dziś' and the focus on portfolio/watchlist changes imply a daily summary use case. However, the description gives no explicit guidance on when to choose this tool over related sibling tools, and no exclusions or alternatives are mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The readOnlyHint annotation is true, and the description does not contradict it. The description adds that the tool provides both historical and future dividends, along with source and freshness, which is useful context beyond the annotation. However, it does not disclose any limitations, data freshness guarantees, or potential error conditions, so it only partially covers behavioral transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence in Polish that directly states what the tool returns and includes key data attributes. It is front-loaded with the core purpose and contains no fluff. Slightly short, but effective for a simple read-only tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only tool with one parameter and no output schema, the description provides sufficient context: it explains the data returned (historical and future dividends, amount, date, source, freshness). There is no critical information missing for an agent to decide whether to invoke it, though it could mention ordering or currency, which is minor.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The sole parameter `symbol` is fully described in the schema as 'Ticker spółki' (company ticker). The tool description mentions 'spółki' but does not add any further semantic detail about the parameter. Since schema coverage is 100%, the parameter is already well-documented, and the description adds marginal value beyond it.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description explicitly states the tool returns a company's dividend history and known future dividends, including amount, date, source, and freshness. This clearly identifies the resource (dividends) and the action (get), distinguishing it from other get_* tools that cover different financial data like earnings or prices.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not explicitly state when to use this tool versus alternatives. The name and content imply it is for dividend-specific queries, but there is no mention of when not to use it or alternative tools (e.g., using get_earnings_calendar for earnings instead). Usage context is implied but not formalized.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The readOnlyHint annotation already covers the safety profile, so the bar for additional disclosure is lower. The description adds some useful context by specifying that the data is 'current' and limited to macro categories, but it does not explain behavior such as how optional forum sentiment rows are appended or how results are presented.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-structured sentence with no filler; the core concept and category list are front-loaded. It is appropriately brief for a simple read-only tool, though the fragment-like phrasing limits its richness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only snapshot tool with fully documented optional parameters, the description is minimally adequate. However, it lacks alternatives, does not clarify the relationship between the optional symbols and the macro categories, and provides no output-shape expectations despite the absence of an output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema fully documents both parameters. The description adds no extra meaning about 'symbols' or 'includeForumSentiment', and the phrase 'nastroje na rynku amerykańskim' is not explicitly connected to the forumSentiment feature described in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Bieżące czynniki makro: surowce, waluty, stopy, nastroje na rynku amerykańskim' clearly identifies the resource as current macro drivers and enumerates specific categories. However, it uses a noun phrase rather than an explicit verb like 'returns' or 'gets', and it does not differentiate this tool from siblings such as macro_attribution or get_factor_context.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is given about when to use this tool versus alternatives, nor are any exclusions or prerequisites mentioned. The description only states what the tool covers, leaving the agent to infer the appropriate context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotation readOnlyHint: true already covers the safety profile, so the bar is lower. The description adds only the 'upcoming' scope, which is implicit in the tool name. It doesn't disclose any additional behavior like pagination, output format, or handling of missing symbols. It's consistent with annotations but adds minimal value beyond them.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence with zero waste, front-loaded with the core purpose. It's appropriately concise for a simple read-only tool. However, it's so brief that it misses any usage nuance, which slightly detracts from optimal structure.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the schema fully covers parameters and the readOnlyHint annotation is present, the description is minimally adequate. However, it doesn't describe the return shape (e.g., list of dates/symbols) or the default behavior (all holdings/watchlist) which is only in the schema. For a tool with no output schema and three optional params, a bit more context would improve completeness, but the schema compensates.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% – all three parameters (symbols, daysAhead, includePast) have detailed descriptions in the schema. The description adds no parameter-specific meaning, so the baseline 3 applies. No extra syntax or context is provided beyond what the schema already states.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states the tool provides a calendar of upcoming periodic reports, which is a clear verb+resource. It distinguishes it from siblings like get_earnings_deepdive (which implies deeper analysis) and get_report_event (singular event). However, it could be more specific about filtering or scope, so it doesn't earn a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no guidance on when to use this tool vs. alternatives. With many sibling tools like get_earnings_deepdive, get_report_event, and get_dividends, the agent gets no differentiation or context on selecting this one. No exclusions or conditions are provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already provide readOnlyHint:true, so safety is covered. The description adds that the output is a qualitative narrative ('what surprised, what worried, what management announced'), which gives context about the return type. However, it does not disclose details like whether it returns text or structured fields, or any potential limitations (e.g., dependency on analyst notes). Given the annotation already covers read-only nature, the description adds moderate value beyond that.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that is concise and informative. It front-loads the core purpose ('Pogłębione omówienie' - in-depth discussion) and lists the key aspects (surprises, concerns, management announcements). There is no wasted wording. It could be slightly more structured (e.g., mention of inputs) but it remains efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only getter with 4 optional parameters and no output schema, the description covers the qualitative nature of the response but does not explain the exact return format or how to interpret the output. Given the presence of many similar sibling tools (e.g., get_company_analysis, get_daily_brief), an agent may need more explicit guidance on what distinguishes this deepdive from others. However, the schema handles parameter clarity, and the tool is straightforward, so a 3 is appropriate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description does not add any additional parameter semantics beyond what the schema already documents. Each parameter (limit, symbol, quarter, symbols) is described in the schema. The description focuses on the tool's purpose, not on parameter details, which is acceptable given the schema completeness.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states what the tool does: it provides an in-depth discussion of a quarterly earnings report, highlighting surprises, concerns, and management guidance. This distinguishes it from siblings like get_earnings_calendar (calendar of dates) and get_quarterly_kpis (quantitative KPIs). It is specific about the resource (quarterly report) and the nature of the output (qualitative deepdive). No explicit mention of symbol/quarter, but the parameter schema covers that, so overall purpose is clear.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for when a deeper qualitative analysis of earnings is needed, as opposed to just data. However, it does not explicitly state when to use this tool versus alternatives like get_report_event or get_company_analysis. There is no direct guidance on when not to use it or what edge cases it serves. The intended use is inferred from the phrasing but not stated explicitly.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, so the agent knows this is safe to call. The description adds useful context about historical scope and index comparison, but does not disclose output shape, default window behavior, or truncation semantics; those are partly covered by schema parameter descriptions.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single compact sentence that front-loads the core idea and includes the outcome comparison. There is no filler or repeated schema information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only tool with 5 optional parameters and no output schema, the description gives enough orientation to understand the intent, and schema documents the parameters. However, it does not clarify what the response contains beyond 'what worked and what didn't', and it does not mention any rate limits or pagination beyond what the limit parameter hints at.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and parameter descriptions already explain defaults, precedence (sinceIso vs days), canonicalization, and hitting behavior. The description adds no parameter-level detail beyond what the schema provides, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific resource (old alert outcomes), the action (settlement/evaluation), and the comparing basis (index), so an agent can tell it is about historical alert performance rather than a generic listing. It does not explicitly differentiate from similar siblings such as get_my_alert_performance or historical_event_hit_rate, which keeps it from a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'dawnych alertów' and 'na tle indeksu' implies this is for retrospective alert evaluations, but there is no explicit when-to-use or exclusion like 'use get_my_alert_performance for user-level performance'. Usage context is inferable yet not stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, so the agent knows this is a safe read operation. The description adds the semantic context that events are 'macro' and 'may move the market' but does not disclose the output format, pagination, or any related constraints. With annotations covering the safety profile, the description carries a moderate burden and provides only minimal behavioral detail beyond that.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence, effectively communicating the core purpose. It is appropriately sized for a simple tool with one optional parameter. However, the use of Polish may hinder universal understanding for an agent expecting English, but this does not affect conciseness. It is efficient with no extraneous words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only calendar tool with one optional parameter and no output schema, the description is adequate but not fully complete. It does not specify what the response contains (e.g., event dates, impact levels) or clarify the differentiation from similar calendars like earnings. Given the absence of an output schema, a bit more detail on the return structure would improve completeness. The tool is relatively low complexity, so a 3 is reasonable.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema provides 100% coverage for the lone parameter daysAhead, including its type and default value. The description adds no additional meaning about parameters, which is acceptable given the schema fully documents them. Per the rubric, baseline 3 is appropriate when the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description, 'Kalendarz zdarzeń makro, które mogą poruszyć rynkiem' (Calendar of macro events that may move the market), clearly identifies the resource as a calendar of macroeconomic events and its purpose. It is distinct from siblings like get_earnings_calendar by focusing on macro events. However, it does not explicitly mention the retrieval action, though the tool name implies it. Overall, the core function is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives such as get_earnings_calendar or get_market_anomalies. It does not state conditions, exclusions, or recommend alternatives. An agent is left to infer usage solely from the resource type, which is insufficient for selecting among many calendar-like tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Description contradicts annotations: it says 'Zmiana' (change) implying mutation, while annotations set readOnlyHint=true. This is a direct annotation contradiction that would confuse an agent about side effects and safety.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single short sentence, but it is both incomplete and misleading. It does not front-load the primary purpose and contains a contradictory verb, so brevity is not an asset here.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

A getter with 4 required parameters and no output schema demands a clear explanation of what context is returned and how parameters relate. The description provides none of that and even misleads about mutation, making it completely inadequate for an agent to call correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all five parameters are documented in the schema. The description adds no extra meaning beyond naming the resource ('macro factor for a company'), so it does not improve on the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description is vague and misleading: it says 'Zmiana' (change) but the tool name is get_factor_context, suggesting it retrieves context. It doesn't clearly state what the tool does or what the output represents, and it fails to distinguish itself from many sibling get_* tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus other factor-related tools like macro_attribution or get_company_analysis. No context about intended scenarios or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The readOnlyHint annotation already communicates safety, and the description adds a meaningful restriction ('Wycena modelowa jest dostępna w PRO') that informs about feature gating. Still, it says nothing about return format, pagination, or failure modes, so transparency is adequate but limited.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short sentences with no filler; the primary purpose is front-loaded. The PRO sentence is slightly promotional but still conveys a real constraint, so it earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only tool with one parameter, the description covers the core idea, but with no output schema and no parameter documentation, the agent lacks enough detail to safely invoke it (e.g., symbol format, what the forecast includes). It is minimally complete but not robust.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has one 'symbol' parameter with zero description coverage, and the description only implies it is a company identifier via 'spółki'. It does not define the expected format (e.g., ticker vs. ISIN) or provide examples, leaving a key ambiguity unresolved.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool provides a forecast of company results for upcoming quarters, specifying both resource ('wyników spółki') and time frame ('najbliższe kwartały'). It is specific enough to distinguish from most siblings, though it doesn't explicitly name alternatives like get_forecast_accuracy.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is given on when to use this tool versus alternatives such as get_forecast_accuracy or get_quarterly_kpis. The PRO note is a feature limitation, not a usage cue, leaving the agent without selection criteria.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark this as read-only. The description adds useful result content (accuracy and quality-gate status), but it doesn't disclose return shape, sorting, pagination, or default behavior beyond what the schema already says.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, front-loaded sentence conveys the core data without filler or repetition. It wastes no token budget.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only tool with only two optional parameters, the description plus schema covers the essential call semantics and the nature of the returned data. It would be more complete if it explicitly described the result as a ranked list, but nothing critical is missing for a basic call.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the description is not required to re-explain limit or symbol. It doesn't add any extra parameter meaning, matching the baseline for fully documented schemas.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a concrete resource—historical accuracy of forecasting models plus a quality-gate flag—which is far more specific than the tool name alone. It doesn't explicitly compare against sibling tools like get_forecast or get_signal_prediction_performance, so it misses the explicit differentiation needed for a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No statement of when to use this tool instead of alternatives is provided. The optional symbol and limit parameters imply a filtering use case, but the description neither states it nor excludes any sibling tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The readOnlyHint annotation already covers the safety profile. The description adds some behavioral context by specifying hourly resolution and session scope, but it does not disclose how far back 'previous sessions' reaches or what the returned candle structure is.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single front-loaded sentence with no filler. It is efficient, though quite terse; useful context about response format or usage is omitted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple read-only nature and good schema documentation for two of three parameters, this is minimally viable. However, with no output schema, an agent is left without information about the candle payload, session/timezone semantics, or behavior beyond the bare scope phrase.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already documents period and intervalSec well, including enums and defaults. The description adds minimal parameter meaning beyond implying hourly bars, and the required symbol parameter has no semantic explanation. This is adequate middle ground given 67% schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states the resource ('hourly candles') and its scope ('current and previous sessions'), which aligns with the tool name. It is clear enough for selection, but it does not explicitly differentiate it from siblings like get_price_series or get_intraday_quote.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives. The description only gives a scope hint; it never mentions exclusions, prerequisites, or sibling tool comparisons.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, so the agent knows it's a safe read. The description adds concrete fields returned (price, open, range, change), but doesn't disclose additional behavioral traits like data freshness, timezone, or intraday session specifics. With annotations covering safety, a 3 is appropriate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is one short sentence, front-loaded with the main purpose, and includes all key fields. It's efficient, though it doesn't mention the sibling alternatives that could have been added.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool is a simple quote fetcher with one well-documented parameter and readOnly annotation, the description is complete. The only minor gap is not specifying anything about data granularity or timing beyond intraday, but for this complexity it's adequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%: the only parameter 'symbols' has a description with examples and a limit of 1-10 tickers. The schema already explains it fully, so the description adds no extra parameter semantics. Baseline 3 is correct.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly indicates it provides intraday quote data including price, open, daily range, and change from previous close. It's a specific resource (quote) and action (get), and while it doesn't explicitly name siblings like get_spot_price or get_price_series, the mention of intraday and change vs prior close differentiates it from general price series.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for intraday quote needs but doesn't explicitly state when to use this versus alternatives like get_spot_price, get_intraday_candles, or get_price_series. It's clear enough for a quote-focused need but lacks explicit exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With only readOnlyHint=true in annotations, the parameter text adds substantial behavioral context: candle-read performance (35 docs/110 kB/163 ms vs 389 docs/1169 kB/356 ms), a 20 s live-quote fan-out budget with fallback to daily closes so the scan 'cannot hang the response,' and the ~$0.05 per-anomaly Sonnet 4.6 cost when synthesis is enabled. This meaningfully exceeds the annotation's coverage.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The main description is a single efficient sentence, but it is terse to the point of under-specification. Meanwhile the symbolsScope parameter description is overloaded: it embeds a historical before/after narrative, a cost measurement, and an anecdote about the ten largest moves, which could be restructured into the current semantics plus a cost warning. Structure is uneven.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 4-parameter tool with no output schema and many sibling scanners, the definition does not state the return shape: fields per flagged anomaly, ordering, limits, or the detection time window (intraday vs end-of-day; the daily-closes fallback hints at candle-based detection but never states it). The parameter descriptions partially compensate by disclosing returned market context and the synthesis text per anomaly, but entry-level return semantics are left to inference.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%: all four parameters have descriptions with defaults, enums, and effect explanations. The tool-level description adds no parameter info, so the baseline 3 applies — the schema does the heavy lifting. The parameter descriptions are unusually rich (especially symbolsScope), but that richness is inside the schema, not additional value from the description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb+resource: automatically catching price moves that deviate from a company's usual volatility. This is clear about what the tool computes. However, it does not differentiate it from near-neighbor siblings such as find_overheat_candidates, find_dip_candidates, whats_moving_now, or run_predictive_scan, all of which plausibly do similar scanning.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied: if you want volatility-deviation anomalies, run this scan. The parameter descriptions offer operational tuning guidance (sigmaThreshold: 'Use 2 for stricter, 1 for noisier'; symbolsScope: cost and universe implications), but there is no explicit statement of when to prefer this tool over the many sibling anomaly/opportunity scanners, and no exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotation already covers read-only safety, and the parameter documentation adds useful behavioral context: filtered results carry `universe` and `alertsOutsideUniverse`, every metric is computed on that market alone, indeterminate-market alerts are excluded, and unfiltered averages mix two source coverage regimes. This gives the agent far more than the bare readOnlyHint would alone.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The actual description is a single tight Polish sentence that front-loads the tool's evaluative purpose. Longer rationale lives in the parameter schema where it belongs, and nothing in the description is redundant or padded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only query, the important constraints are well covered: annotations declare safety, all parameters are documented, and the `universe` rationale explains scope-dependent behavior. The only meaningful gap is that no output schema exists and the description does not precisely specify the return shape beyond the general notion of how many alerts 'proved correct.'

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3; the schema already documents defaults, max lookback, deprecation, uniqueness constraints, and the universe enum semantics. The tool description itself adds no parameter-level detail beyond what the schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The Polish description states a clear verb+resource: it evaluates the alerts the user received and how many turned out correct, so the core purpose is understandable. It does not explicitly distinguish itself from siblings like get_alert_delivery_stats or historical_event_hit_rate, so an agent has to infer the difference from the personal 'które dostałeś' phrasing.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The main description gives no explicit when-to-use guidance or named alternatives, but the `universe` parameter documentation supplies strong context: it explains when filtering by market matters shouldn't be skipped and why unfiltered hit rates can be misleading across two very different data sources. There are no exclusions, but the scoping guidance is clear enough to guide correct usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

readOnlyHint=true already covers the safety profile, and the description adds that evaluations are returned alongside news. It does not describe ordering, pagination, or what the 'assessment' actually represents, but there is no contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no redundant wording. Every word contributes to identifying the tool's purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With seven parameters and no output schema, the one-line description leaves the meaning of returned evaluations and selection context under-specified. The detailed schema covers invocation mechanics, but not the absent output/behavior richness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all seven parameters are documented in the schema. The description adds no parameter-specific meaning beyond what the schema already provides, which warrants the baseline score.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description states a specific resource (company dispatch/news history) and the added value (evaluations/assessments), making the tool's purpose clear. It does not explicitly differentiate from sibling get_* tools, so it misses the top score.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance, prerequisites, or alternatives are described. The agent must infer when to choose this over similar tools like get_company_analysis or get_activity_feed.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With readOnlyHint already set, the description does not need to argue safety; it adds the target scope of alerts and forecasts. But it does not explain what the health/status contains, how it is computed, or any access caveats.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single short phrase with no filler; the key domain words are up front. It is appropriately sized for a parameterless status endpoint, even if the content is thin.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema exists, so the description is the only hint about the return value. It gives a general subject ('state of settlement of alert/forecast results') but leaves the health semantics vague. For a zero-parameter read-only tool this is minimally viable but not complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters, so the input schema already covers everything. Therefore the description has no parameter-meaning burden.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies a specific resource – the settlement state of alert and forecast outcomes – and is more specific than the name alone. However it lacks a verb and does not distinguish the tool from similar getters like get_evaluation_outcomes or get_forecast_accuracy.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when/when-not guidance is provided, and no alternative tools are named. The only implied use is 'check this state,' which does not help an agent choose among the many alert/forecast-related siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark the tool as read-only, and the description adds the behavioral scope: it reports freshness, delays, and failures. It does not describe return format, aggregation, or side effects, but for a read-only status tool the safety profile is covered by annotations. No contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single compact phrase that lists three relevant aspects without filler. It is appropriately short and front-loaded with the resource, though its brevity limits the amount of useful context it can convey.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only health tool with one optional parameter, the description plus schema and annotations is minimally viable. It lacks an explicit output contract, a list of covered pipelines, and usage alternatives, so it is not fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3 even without parameter details in the tool description. The tool description itself adds no parameter-level meaning; the schema's parameter text is detailed but somewhat tangential and verbose.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies the resource (data pipelines) and the key health dimensions (source freshness, delays, failures), making the purpose recognizable. However, it is a noun phrase without an explicit verb and does not differentiate from sibling tools like get_codex_pipeline_stats or get_outcome_settlement_health.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives such as get_codex_pipeline_stats or get_alert_delivery_stats. No prerequisites, exclusions, or contextual triggers are provided; usage is only implied by the name and the noun phrase.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

readOnlyHint=true already covers the safety profile, lowering the bar. The description adds the specific computed metrics (daily curve, return, drawdown, volatility, benchmark comparison) which is useful substantive context. No contradiction with annotations, but no extra behavioral detail like response format or data granularity is disclosed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence with zero waste states the core output (capital curve) first, then lists metrics compactly. It is genuinely concise, though written in Polish rather than English.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only analytics tool with two optional, fully-documented parameters and readOnlyHint set, the description adequately conveys the deliverables. The main gap is the absence of an output schema and hence any statement about the return structure, which is minor given the tool's simplicity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% — period and benchmark are both fully documented with enums, defaults, and explanatory descriptions of what WIG/SPY/QQQ represent. The description's mention of 'WIG or S&P 500' partially duplicates the schema's benchmark enum. Baseline 3 applies since the schema does the heavy lifting.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names specific outputs — daily capital curve, return rate, drawdown, volatility, and benchmark comparison — making the resource and purpose concrete. However, it is a noun phrase without an explicit verb, and it does not name any sibling tool to distinguish itself from the many get_portfolio_* alternatives.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is given on when to use this tool versus the numerous siblings (get_portfolio_value_history, get_portfolio_stats, get_total_portfolio_view). The description implies portfolio performance analysis but provides no exclusions or alternative-routing cues, leaving selection to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

readOnlyHint=true already covers the safety profile, and the description adds a genuinely useful behavioral constraint: analysis/valuation content requires a PRO plan, which tells the agent a call may be gated. It does not mention pagination or response shape, but the PRO disclosure is real added context beyond annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two tightly packed sentences: content list first, plan constraint second. No filler, front-loaded. The content enumeration is dense but each element earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only, single-parameter tool with no output schema, the description adequately covers what is returned (the listed sections) and the PRO gate. Nothing critical is missing, though the section list also lives in the schema so there is mild overlap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and the 'include' enum is fully documented in the schema (omission = full response, unknown value = error). The description adds no further parameter meaning, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb/resource ('Obraz portfela użytkownika') and enumerates the content it surfaces: positions, cash, watchlist with analyst rating/reason, allocation goals. Clear purpose, but it never distinguishes itself from the many sibling portfolio tools (get_total_portfolio_view, get_portfolio_stats, get_portfolio_analytics), which an agent must choose between.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives one usage condition ('Analiza i wycena wymagają PRO') that flags a plan gate, but offers no when-to-use/when-not guidance and no routing among the crowded set of sibling portfolio tools. Usage is only implied, not stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The readOnlyHint annotation already establishes that this is a safe read operation. The description adds a useful behavioral detail by noting the statistics are computed from transaction history, but it does not disclose aggregation behavior, output shape, or data limitations beyond what the schema already implies.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single compact line with no filler. It front-loades the tool's purpose and its computation basis, so every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description offers only a general sense of what will be returned ('risk and performance statistics'), without specifying the exact metrics or output shape. The read-only annotation and fully described parameters compensate partially, but an agent still lacks enough detail for confident invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all six optional parameters are already documented with their meanings and defaults. The tool description adds no parameter-level guidance, matching the baseline case where the schema carries the semantic burden.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the resource and scope: portfolio risk and performance statistics based on transaction history. It lacks an explicit verb and does not differentiate it from near-siblings like get_portfolio_analytics or get_portfolio_context, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus the many similar portfolio/risk siblings, and no exclusions or prerequisites are mentioned. The only implied context is that transaction history is required, which is not enough to reliably route an agent.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The readOnlyHint annotation already indicates a safe read operation, so the description does not need to restate that. However, the description adds no additional behavioral context such as pagination, default time range (though that is in the schema), data granularity, or how the history is constructed. With annotations covering safety, the minimal description offers little extra transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is very short and free of fluff, which is good, but it is under-specified. It is a single phrase that does not elaborate on the nature of the returned data or any important nuances. It is concise but lacks the structure that would make it genuinely useful.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the low complexity (one optional parameter, no output schema), the description is still incomplete. It does not describe the return format (e.g., array of {date, value}), the frequency of data points, or whether the current value is included. Since there is no output schema, the description should fill that gap, but it does not.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has 100% coverage for the single 'days' parameter, including default, min, max, and a clear description. The tool description adds nothing about the parameter, but the baseline of 3 is appropriate because the schema fully documents it.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states the resource (portfolio value) and the time dimension (history over time), so the core purpose is discernible. However, it is vague about the exact output (e.g., a time series of values, frequency, currency) and does not differentiate from sibling tools like get_portfolio_analytics or get_total_portfolio_view. It is not a tautology, but it lacks specificity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus the many related portfolio get_* tools. The description does not mention alternatives, exclusions, or typical use cases. An agent must infer usage solely from the name and generic description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already declare readOnlyHint=true, and the description's 'list' wording is consistent with that. The description adds only the 'tracked' scope and does not mention return shape, ordering, pagination, or other runtime behavior. There is no contradiction with the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single short phrase with no filler words. The operation is front-loaded, and every word contributes to the meaning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The schema covers parameters well and the read-only annotation covers safety, but the description is minimal. It does not define what a 'priced event' is, does not describe return values, and does not help an agent choose this over sibling event-related tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with all six optional parameters documented, including defaults, enums, and the universe/universeFilter alias. The description itself adds no parameter-level meaning, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the operation ('Lista' = list) and the resource ('śledzonych zdarzeń wycenionych' = tracked priced events). It is specific enough to be understood, but it does not explicitly differentiate itself from related siblings like get_evaluation_outcomes or get_report_event.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance about when to use this tool versus related event tools such as track_priced_event, resolve_priced_event_now, or get_event_risks. No exclusions, prerequisites, or alternative conditions are provided, so the usage context must be inferred entirely from the name and sibling list.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotation readOnlyHint=true already communicates safety, and the description adds that the output includes both OHLC bars and realized volatility. It does not go deeper into behavioral details like period precedence, clamping, or subscription requirements, but some of that is captured in the schema. No contradiction with annotations exists.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single compact sentence with no filler, and the core output is presented first. The dash-separated use-case clause makes it slightly telegraphic, but every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The schema already covers interval and lookback semantics, and readOnlyHint covers the safety profile. The description supplies the output composition and use case, but with no output schema and no explicit differentiation from get_intraday_candles, the agent is left to infer the exact return shape and when this tool is the correct choice.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description adds no parameter-level guidance. The required parameter 'symbol' has no schema description and the description doesn't clarify it. The other parameters are explained reasonably well in the schema, so the tool description contributes essentially no additional parameter meaning.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states exactly what the tool returns: OHLC candles and realized volatility. This makes the resource clear and distinguishes it from siblings like get_spot_price. However, it doesn't explicitly differentiate from get_intraday_candles, so it stops short of full sibling differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'do stop-lossów i wielkości pozycji' provides a concrete intended use case: stop-loss placement and position sizing. This implies when the tool is useful, but it does not explicitly state when to prefer this tool over alternatives or mention any exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint=true, so the safety profile is covered. The description adds a unique behavioral trait: each line includes a quality assessment, which is useful context beyond the annotations. However, it doesn't detail return format or pagination, which is acceptable given read-only nature.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, concise and to the point, with the main purpose front-loaded. No wasted words, though it could be slightly more structured with separate fields, but it's efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's moderate complexity, the description covers what data is returned and the unique quality assessment. With annotations indicating read-only and schema fully covering parameters, it's sufficiently complete, though it could mention the default quarters back behavior, but that's in schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so parameters symbol and quartersBack are fully documented. The description doesn't add extra meaning beyond the schema, but the baseline 3 is appropriate since schema covers everything.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states it returns quarterly results including revenue, profit, balance sheet, and cash flows, plus a quality assessment of each line, which is specific and clear. However, it doesn't explicitly differentiate from siblings like get_earnings_deepdive or get_company_analysis, so it lacks sibling differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for retrieving quarterly KPIs but doesn't explicitly state when to use this tool versus alternatives like get_earnings_deepdive or get_company_analysis. Some context is given by listing the data fields, but no exclusions or alternative mentions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The only annotation is readOnlyHint: true, which the description does not add to. It does not disclose what data is returned, whether rankings are historical or current, any assumptions, or potential limitations. For a read-only operation, the description adds minimal behavioral context beyond the annotation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single vague sentence. While it is concise in length, it is under-specified and does not adequately convey the tool's purpose. It fails to earn its place by providing any actionable information for the agent.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With only one parameter, no output schema, and a readOnlyHint annotation, the description still leaves critical gaps: what is the ranking? How is performance measured? What does the output look like? The tool is incomplete for an agent to understand its full behavior without additional information.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% for the single parameter horizonDays, which is fully documented in the schema with type, default, range, and meaning. The description itself mentions no parameters, so it adds no value beyond the schema. Per the rubric, with high coverage, baseline is 3, and the description does not exceed baseline.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Jak ranking sprawdzał się w przeszłości' (How the ranking performed in the past) indicates the tool is about historical performance of a ranking, but it is vague. It doesn't specify which ranking, what metrics, or how it differs from siblings like get_stock_rankings or get_signal_prediction_performance. The verb 'sprawdzał się' (performed) is imprecise and does not clearly establish the resource.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool vs. alternatives. No context about what kind of ranking, what use case it serves, or any exclusions. The description provides no situational cues, leaving the agent without direction on when this tool is appropriate compared to the many similar 'get_*' siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The readOnlyHint annotation already signals a safe read operation, and the description adds the year-to-date scope and the tax-loss opportunity output. It does not disclose calculation assumptions, response shape, or behavior for an invalid year, but for a read-only getter with annotations this is adequate.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One sentence conveys both main outputs with no filler or redundant restatement of the tool name. It is front-loaded around the core purpose and the tax-loss opportunity add-on.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple one-parameter read-only tool, the description plus schema covers what the tool returns and the optional year input. A short note on what the returned tax-loss opportunities look like would have made it fully complete, but nothing is missing that would prevent a correct call.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema fully documents the single optional year parameter with its default behavior, so the schema carries the burden. The description does not discuss the parameter, but it does not need to at this coverage level.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific resource: realized P&L since the beginning of the year, plus tax-loss harvesting opportunities. This is more than a restatement of the tool name, though it does not distinguish itself from sibling get_* tools such as get_transaction_history, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The intended use is implied by the content: call this when the user needs year-to-date realized P&L or tax-loss harvesting ideas. However, there is no explicit when-to-use guidance, no exclusions, and no pointer to an alternative sibling.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint=true, so the agent knows this is a safe read operation. The description adds context about what the event contains (narrative, settlements, changes, open items, age/source of figures), which is useful. It doesn't disclose pagination, response size, or any rate limits, but for a read-only retrieval tool this is acceptable.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, information-dense sentence in Polish. It front-loads the core purpose and enumerates the report's contents compactly. It could be slightly more structured, but it earns its place with no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only retrieval tool with a clear schema and no output schema, the description covers the conceptual content well. However, it doesn't explain the relationship between `eventId` and `quarter` (e.g., which takes precedence) beyond the schema's note, and it doesn't clarify what 'event' means in this domain. The sibling list is large, but the description is enough to distinguish it from most.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 67%: `eventId` and `quarter` are documented in the schema, while `symbol` is not. The description doesn't add parameter-level detail beyond the schema, but the schema already covers the two most nuanced parameters. The description's mention of 'age and source of each figure' hints at what `quarter` and `eventId` control, but not explicitly.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource: it presents a quarterly report as an event, summarizing what it says, what it settled, what it changed, what remains open, with age and source for each figure. This is clear and distinct from generic report tools, though it doesn't explicitly name a sibling alternative.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the tool is for retrieving a quarterly report event with detailed breakdowns, and the schema clarifies that `quarter` can be omitted for the most recent report. However, it doesn't explicitly state when to prefer this over siblings like get_quarterly_kpis or get_earnings_deepdive, nor does it state exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

readOnlyHint=true already tells the agent this is a safe, non-mutating read, which lowers the burden on the description. The description adds that the output combines a risk level with active drivers, but it omits scope (market-wide vs portfolio), the scale of the level, and whether results are cached or time-sensitive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single sentence that is front-loaded with the resource and its two components, with no filler. It is efficient, though slightly terse for an aggregate dashboard tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no input parameters and no output schema, the description carries almost the full burden, and it only partially meets it. It says what the dashboard shows but not how it relates to sibling risk tools or what the level/driver fields mean, which is a meaningful gap given the crowded risk-tool family.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline for a no-argument tool is 4. No parameter-related information is missing.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies the resource (market risk) and the content returned (risk level plus active drivers), so the purpose is discernible. However, it never distinguishes itself from closely related siblings such as get_risk_regime, get_risk_themes, or get_event_risks, leaving the agent unsure which risk tool this aggregate view supersedes.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no statement of when to use this dashboard versus the many other risk-related tools (get_risk_regime, get_risk_themes, get_concentration_risk, macro_attribution). No prerequisites, scope, or alternatives are given, so usage must be inferred purely from the name.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The readOnlyHint=true annotation already establishes this is a safe read, lowering the bar. The description contributes the useful fact that the result is a categorical regime label (calm / mild nervousness / strong nervousness / crisis), which is real behavioral information not present in annotations or any output schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single short fragment with zero filler and the key information front-loaded. It is efficient, though the terseness edges into under-specification rather than optimal conciseness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the burden of explaining the return value, and it only partially does so — it lists the regime categories but does not say whether the result is a single label, a score, a history, or a time horizon. For a zero-param read tool the input side is trivially complete, so the gap is moderate rather than severe.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool takes zero parameters, so the baseline is 4. There is nothing for the description to clarify on the input side, and it does not attempt to.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the resource (market risk / 'Ryzyko rynkowe') and enumerates the possible regimes, so an agent can infer it returns a market-risk classification. However, there is no verb at all — it is a fragment, not a statement of what the tool does — and nothing distinguishes it from siblings like get_risk_dashboard, get_risk_themes or get_concentration_risk.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No when-to-use guidance, no prerequisites, and no mention of any alternative among the many risk-related siblings (get_risk_dashboard, get_risk_themes, get_concentration_risk). The agent must guess when this is the right call versus those.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The readOnlyHint annotation already covers safety, so the description's burden is lighter. It adds only the temporal notion that the themes are currently active, but provides no detail about output shape, interpretation, or limitations. This is minimal additional behavioral disclosure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no filler. It captures the core purpose efficiently and is appropriately sized for such a simple tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter read-only tool, the description is minimally sufficient. However, with no output schema, it would benefit from explaining what a 'risk theme' result looks like and how this differs from related risk tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The tool has zero parameters and 100% schema description coverage, so the description is not required to add parameter-level meaning. The baseline for a zero-parameter tool is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states the resource: 'risk themes' that are active at the current moment. It is clear about what the tool returns, though it does not explicitly differentiate itself from sibling tools like get_risk_dashboard or get_event_risks.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is given about when to use this tool versus alternatives. The only contextual hint is 'at this moment,' but there are no exclusions, prerequisites, or references to sibling tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

readOnlyHint=true already marks this as a read-only operation, and the description does not contradict that. The description adds useful output-oriented context (hits, direction, mean error), but it does not disclose behavioral details such as evaluation window, aggregation, or relationship to other prediction metrics. This is acceptable but minimal given the annotation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, efficient sentence with a useful colon-separated list of the reported metrics. It has no filler and communicates the core purpose quickly, though it sacrifices some behavioral and comparative context for brevity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description names key output concepts but there is no output schema, so the agent cannot infer the exact return shape, units, or evaluation period. The heavy overlap with sibling accuracy/performance tools is not addressed, though for a read-only tool with zero required parameters and well-documented filters, the description is minimally adequate.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, and each parameter already has meaningful documentation: kind has example values, symbol notes server-side canonicalization of GPW aliases, and universe states its default. The tool description adds no parameter-level meaning beyond the schema, so the baseline score of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description identifies the resource (numerical price-movement prediction accuracy) and names three concrete metrics: hits, direction, and mean error. It is clear about what the tool reports, though it does not explicitly differentiate it from similar siblings like get_forecast_accuracy or get_ranking_performance.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no guidance on when to use this tool versus alternatives such as get_forecast_accuracy, get_my_alert_performance, or get_ranking_performance. The optional filters are present in the schema, but no scenario or exclusion criteria are described.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The readOnlyHint annotation already establishes the safe read-only nature. The description adds meaningful behavioral context by stating that the response indicates whether the price is from market close or from an intraday quote, which helps set expectations for data source and timing.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single focused sentence that conveys the essential purpose and output nuance without any filler. It is front-loaded with the core action and keeps the added detail about quote source tight.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only tool with one parameter and no output schema, the description covers the main return characteristics: current price and its origin. It falls short only in not specifying symbol format or currency, but the low complexity makes the definition reasonably complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema provides only the parameter name 'symbol' with no description, and the description does not elaborate on the expected format, exchange, or uniqueness of the symbol. The phrase 'jednej spółki' offers minimal context that the value identifies a single company, but it is still mostly left to inference.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies a single-company spot price lookup and adds the key distinction of whether the price comes from the close or an intraday session quote. This is specific enough to separate it from siblings like get_price_series and get_intraday_quote, though it does not name them explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives such as get_intraday_quote or get_price_series. The description states what it returns but not the conditions that would make it the preferred choice.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The readOnlyHint annotation already covers the safety profile, so there is no contradiction. However, the description itself discloses no behavioral detail beyond the tool's basic purpose—nothing about what a 'run' is, whether results are static snapshots, or what the output structure looks like.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single declarative sentence with zero filler or repetition. It is immediately readable and front-loaded, earning its place by stating the core purpose without verbosity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 5-parameter tool with no output schema, this description is too thin. It does not explain what the returned ranking contains, the meaning of a 'published run', or how the category filters affect ordering. The schema fills the parameter gaps, but the overall context remains incomplete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so parameters are already well documented. The main description adds no parameter-level meaning, but the schema descriptions (e.g., category sorting behavior, minAdvPLN defaults) compensate fully, keeping this at the baseline of 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the resource (WSE/GPW companies) and the general operation (ranking by a selected criterion). It is clear enough to distinguish this from non-ranking tools, but it does not explicitly differentiate from sibling ranking tools like get_ranking_performance or rank_revenue_growth.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. It does not mention the 'published run' mechanism, when a dateKey is needed, or how category selection changes the ranking, leaving the agent to infer usage entirely.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations declare readOnlyHint=true, which the description does not contradict. The description adds useful behavioral context: only evidence-backed dimensions are included (max six), liquidity is shown separately and not scored, and detailed dimensions/justification require PRO. This goes beyond the annotations and gives the agent a clearer picture of what the result will contain.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences in Polish and conveys the core purpose, score range, PRO gating, and the evidence/liquidity rules without excess. It is front-loaded with the main action. It could be slightly more structured (e.g., separating the scoring rules), but it is efficient and earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read-only tool with two parameters and no output schema, the description covers the key aspects: what is scored, the range, PRO limitations, and the scoring criteria. It does not explicitly state the return format (e.g., just a number or an object with dimensions), but the PRO note implies a richer structure for premium users. This is a minor gap given the tool's simplicity and the annotation coverage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with both 'symbol' and 'days' well-described (symbol aliases, days lookback range/default). The tool description adds no parameter-specific detail, so it does not enhance the schema. Since the schema already carries the full parameter meaning, a baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it evaluates a GPW company and returns a score from 0-100, which is a specific verb-resource pair. It also notes that dimensions and justification are PRO-gated, adding specificity. However, it does not differentiate from sibling tools like get_company_analysis or get_stock_rankings, which also deal with stock evaluation, so it lacks explicit sibling distinction.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no guidance on when to use this tool versus alternatives. It does not mention any conditions or exclusions, and it does not reference any sibling tool. The only contextual clue is that it is for GPW companies, but that is too vague to steer an agent toward or away from this tool among the many get_* siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.