Gnomad

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

Annotations already indicate read-only and open-world behavior. The description adds valuable context: it routes questions, fills arguments, and returns structured answers with stable citation URIs. This goes beyond the annotations without contradicting 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 front-loaded with the key instruction to prefer over web search, followed by examples. While slightly lengthy, every sentence adds value, and the structure is logical and clear.

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 no output schema, the description sufficiently explains what the tool returns (structured answers with citation URIs) and covers a wide range of use cases. It provides a complete picture of the tool's capabilities and output format.

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?

With 100% schema coverage and a single parameter described as 'Your question or request in natural language', the description enhances understanding by specifying the types of questions to ask and the expected scope (e.g., 'current US unemployment rate').

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 purpose: routing questions to appropriate sources and returning structured answers with citations. It explicitly distinguishes itself from web search and provides concrete examples, making the purpose unmistakable.

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 strong guidance on when to use this tool (factual questions about real-world data) and implies it should be preferred over web search. However, it does not explicitly contrast with other sibling tools on the same server, like search or entity_profile, which could create ambiguity.

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, openWorldHint=true, destructiveHint=false. The description adds valuable behavioral context: it resolves the market, classifies bet type, fans out to relevant packs, and returns a comparison. It does not contradict annotations and supplements them with concrete processing details.

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 paragraph of 3-4 sentences that is efficient and front-loaded. It covers purpose, input, process, and output without wasted words. Could be slightly improved with bullet points for scanned readability, but overall concise.

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 only 2 parameters, no output schema, and no nested objects, the description is fully complete. It describes the input, the internal fan-out logic, and the output (evidence packet and comparison). It provides enough context for an agent to understand exactly what happens and what is returned.

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 new semantic meaning beyond what is in the schema for both parameters. It repeats the input types for 'market' and enum values for 'depth', but does not explain nuances like format requirements or handling of different inputs.

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 purpose: research a Polymarket bet by pulling Pipeworx data. It specifies input types (slug, URL, question text) and output (evidence packet with market-vs-model comparison). It distinguishes itself as the core demo product that improves conversion, setting it apart from siblings like validate_claim or compare_entities.

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 explicit use cases: 'should I bet on X?', 'what does the data say?', 'is there edge in this bet?'. It implies this tool is preferred over discovering packs manually but does not explicitly exclude alternative sibling tools or state when not to use it. The guidance is strong but lacks explicit comparison.

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, openWorldHint, non-destructive. Description adds value by detailing data sources (SEC EDGAR/XBRL, FAERS, FDA, trials) and output format (paired data + pipeworx:// URIs). No contradictions.

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?

Description is concise with about 4-5 sentences, front-loaded with main purpose. Each sentence adds specific, non-redundant information. Well-structured for quick reading.

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 (two entity types, multiple data sources), the description covers use cases, constraints (2-5 items), data sources, and output format. No output schema, but description adequately explains return value. Lacks mention of error handling or pagination, which are not critical for this comparison 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 coverage is 100% with descriptions for 'type' and 'values'. Description adds context by explaining that 'company' pulls financial metrics and 'drug' pulls adverse events/approvals/trials, and gives example values. This enriches understanding 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?

Clearly states the tool compares 2–5 companies or drugs side by side, with specific use-case examples like 'compare X and Y', 'X vs Y'. Distinguishes between two entity types and explicitly contrasts with siblings by saying it replaces 8–15 sequential agent calls.

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?

Provides explicit when-to-use scenarios (e.g., user says 'compare X and Y', wants tables/rankings). Differentiates between company and drug with specific data sources. Does not explicitly state when not to use, but implies alternatives by mentioning replacement of sequential calls.

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 and destructiveHint=false, so the agent knows this is a safe read operation. The description does not contradict these and adds minimal behavioral context beyond explaining the return format. It doesn't disclose any hidden traits like authentication or rate limits, but with annotations present, the bar is lower.

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 few sentences long, well-structured: purpose first, then usage, then examples. It is not overly verbose, and every sentence adds value. Could be slightly shorter but is 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 no output schema, the description tells what is returned ('names + descriptions'), which is sufficient for a discovery tool. The tool has only 2 parameters and no nested objects, and annotations cover safety. The description is complete enough for an agent to use 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 coverage is 100% for both parameters (query and limit). The description implicitly links 'limit' to 'top-N' and gives example queries for the 'query' parameter, but these do not add significant new meaning beyond the schema definitions. 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 starts with a clear verb+resource: 'Find tools by describing the data or task.' It lists specific domains (SEC filings, financials, etc.) and states the return value: 'top-N most relevant tools with names + descriptions.' This distinguishes it from siblings like 'search' which is for general search, not tool discovery.

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?

Explicitly states 'Call this FIRST when you have many tools available and want to see the option set (not just one answer).' This gives a clear usage context and prioritization hint. It also lists scenarios like 'browse, search, look up, or discover' but does not explicitly exclude alternatives or state when not to use it.

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 indicate read-only, open-world, non-destructive. Description adds that it returns citations and lists data sources. Could mention potential data incompleteness, but transparent overall.

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?

Front-loaded purpose, but paragraph is moderately long. Each sentence is informative with no waste, but could be slightly more concise.

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, but description fully explains what is returned (filings, fundamentals, patents, news, LEI, citations). Covers input formats, use cases, and alternatives. Complete for an aggregation 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 coverage 100% with descriptions. Description adds practical details: 'ticker or zero-padded CIK', 'use resolve_entity for names', and clarifies type enum is currently only 'company'.

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 'Get everything about a company in one call' with specific examples like 'tell me about X'. It distinguishes from siblings by mentioning it replaces calling 10+ pack tools, and the tool is unique among siblings like search or resolve_entity.

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?

Explicit guidance: use when user asks for a company profile or would otherwise need multiple tools. Also specifies not to use for names, directing to resolve_entity first.

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 indicate destructiveHint: true, so the description does not need to reiterate destructiveness. It adds value by explaining the tool clears 'sensitive data,' which goes 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 two sentences, front-loaded with the action, and every sentence earns its place without 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 tool is simple with one parameter and no output schema. The description is complete enough to understand its purpose and usage, especially with supportive annotations.

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 100% of parameters, and the description does not add significant meaning beyond the schema's description of the 'key' parameter. 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 'Delete a previously stored memory by key,' providing a specific verb and resource. It distinguishes itself from siblings like 'remember' and 'recall' by focusing on deletion.

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 explicitly states when to use the tool ('when context is stale, the task is done, or you want to clear sensitive data') and mentions pairing with related tools ('remember' and 'recall').

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 and destructiveHint=false, so the safety profile is clear. The description adds input format but does not disclose additional behavioral traits beyond what 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 sentence with no waste. It conveys necessary information efficiently, though it could be structured with separate lines for input and behavior.

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 lookup tool with annotations, the description covers input format but omits output format, error conditions, or pagination. Given the tool's complexity, it is minimally adequate but could be more 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 0%. The description explains the required 'gene_symbol_or_id' parameter accepts a symbol or Ensembl ID, but does not explain the optional 'dataset' parameter. With low coverage, the description partially compensates but is incomplete.

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 retrieves gene information and variants, and specifies it accepts a gene symbol or Ensembl gene ID. This distinguishes it from sibling tools like 'transcript' and 'variant' which focus on other entities.

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 gene lookups but does not explicitly state when to use this tool versus alternatives. No exclusions or when-not guidance is provided, though the context of sibling tools suggests it is the primary gene lookup tool.

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 discloses important behavioral traits beyond annotations: rate limiting ('Rate-limited to 5 per identifier per day'), cost ('Free; doesn't count against your tool-call quota'), and how the team processes feedback ('The team reads digests daily and signal directly affects roadmap'). Annotations only indicate readOnlyHint false, openWorldHint false, destructiveHint false, so the description adds significant value.

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 concise and front-loaded: the first sentence states the core purpose. Every sentence adds value, covering usage, behavioral details, and formatting tips. No wasted 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 feedback tool with 3 parameters and no output schema, the description is complete. It covers purpose, when to use, how to structure feedback, rate limits, and impact. The agent has all necessary information to use 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 baseline is 3. The description adds meaning beyond the schema by explaining the enum values for 'type' (e.g., 'bug = something broke or returned wrong data') and providing context on how to fill in 'message' (e.g., 'Be specific (which tool, what error, what data was missing). 1-2 sentences typical'). This extra guidance justifies a 4.

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 purpose: 'Tell the Pipeworx team something is broken, missing, or needs to exist.' It specifies the types of feedback (bug, feature, data_gap, praise) and distinguishes it from other tools by emphasizing it's for reporting issues to the Pipeworx team, not for general queries.

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 explicitly states when to use this tool: 'Use when a tool returns wrong/stale data (bug), when a tool you wish existed isn't in the catalog (feature/data_gap), or when something worked surprisingly well (praise).' It also provides guidance on how to write the message, including what to avoid ('don't paste the end-user's prompt').

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 discloses the tool's behavior in detail: it walks child markets, checks ordering within events, searches for related markets across events, groups them, and checks monotonicity. Annotations already declare readOnlyHint=true, and the description adds transparency about internal logic and output (ranked opportunities with reasoning). No contradictions 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 concise and well-structured, using clear labels for the two modes. Every sentence adds value, with no redundant information. It front-loads the purpose and briefly explains the mechanics, making it easy to read.

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 covers both modes of operation, provides examples, explains the underlying checking logic, and specifies the return format (ranked opportunities with direction and reasoning). This is sufficient for an agent to understand and invoke the tool correctly, even without 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?

The input schema has 100% description coverage, providing detailed meanings for both 'event' and 'topic' parameters. The tool description reinforces these but does not add significant extra semantics beyond the schema descriptions, so a baseline score 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 the tool finds arbitrage opportunities on Polymarket by checking monotonicity violations. It specifies two distinct modes ('event' and 'topic') and explains what each does, making the purpose precise and distinguishing between the modes.

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 explains when to use each mode: single-event mode for a specific event slug, cross-event mode for related markets across separate events. It provides an example scenario (May vs June cutoffs) where cross-event mode is necessary, but does not explicitly mention when not to use this tool or compare 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 description discloses detailed behavior beyond annotations: scanning top markets, grouping by asset, fetching price history once, using a lognormal model (FRED + coinpaprika), ranking by edge magnitude, and returning suggested trade directions. This fully informs the agent about the tool's internal process and safety (read-only, non-destructive).

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 relatively long but each sentence adds value: first sentence states purpose, second explains mechanics, third states output, fourth gives use case. It is well-structured and front-loaded with the core action. Slight redundancy with schema defaults prevents a 5.

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 sufficiently explains the return format (top N ranked by edge magnitude with suggested trade direction). It also covers the model, data sources, and filtering logic, leaving no critical gaps for an agent to 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 coverage is 100%, so parameters are already well-described. The description adds minimal extra meaning beyond confirming defaults (e.g., limit default 10, window default 1wk). It does not introduce new semantic constraints or examples. 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 the tool scans high-volume Polymarket markets, finds disagreements between Pipeworx data and market prices, and returns top edges. It specifies scope (crypto-price bets, V1) and use case ("what should I bet on today"). While sibling differentiation is not explicit, the core purpose is unambiguous and distinguishes from generic search 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?

The description provides clear context (discovering opportunities without manual browsing) and scope (crypto-price bets). However, it does not explicitly state when not to use this tool or mention alternatives like polymarket_arbitrage, leaving some ambiguity about usage boundaries.

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, destructiveHint=false, so safety profile is clear. Description adds context: listing all keys when omitted, scoped to identifier, and pairing with other tools. 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?

Two sentences, no fluff, front-loaded with verb and resource. Every sentence adds value.

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 one optional parameter and no output schema, the description fully explains behavior, use case, and scoping. Complete for this tool's 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 has 1 parameter with 100% coverage. Description adds that omitting key lists all keys, and explains scoping, going beyond 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 it retrieves a value saved via remember or lists all saved keys when key is omitted. It distinguishes itself from siblings remember and forget, which are named.

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?

Explicitly says when to use ('look up context the agent stored earlier') and pairs with remember/forget for full workflow. Mentions scoping and omission behavior.

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 significant context beyond annotations, detailing the parallel fan-out to three sources and the return structure (structured changes, total_changes, citation URIs). Annotations already indicate read-only and open world, and the description complements them without 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 concise, front-loaded with purpose, and each sentence serves a distinct function (purpose, usage examples, data sources, parameter format, return structure). No wasted 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?

The description covers the purpose, inputs, behavior, and return structure, which is good for a tool with no output schema. However, it lacks details on potential limitations (e.g., pagination, request frequency) and does not elaborate on the structure of 'structured changes' beyond counting, so a minor gap remains.

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?

With 100% schema coverage, the baseline is 3. The description adds value by explaining the `since` parameter formats (ISO date and relative shorthand with examples), clarifying `type` is limited to 'company', and describing `value` as ticker or CIK. This aids correct parameter usage.

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 purpose ('What's new with a company in the last N days/months?') and provides concrete user query examples, making it easy to understand when to use it. It also lists the data sources (SEC EDGAR, GDELT, USPTO), distinguishing it from sibling tools like entity_profile or search.

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 explicitly provides usage scenarios with example queries ('use when a user asks...'), which is highly helpful. However, it does not explicitly state when not to use the tool or mention alternatives, leaving a slight gap in 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 a size recommendation beyond annotations, which already indicate read-only and non-destructive. No other behavioral traits like rate limits or permissions are 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?

The description is a single sentence, which is concise but lacks structure. It front-loads the purpose but is too brief to be fully informative.

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 4 parameters, no output schema, and a sibling set including similar tools, the description is incomplete. It fails to mention output format, pagination, or the dataset parameter.

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?

With only 25% schema coverage (only chrom has description), the description does not explain the meaning of start, stop, or dataset. It implicitly defines the region but adds little parameter-level 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 states that the tool returns variants in a genomic region, with a size recommendation. The verb is implied (list/get), and it distinguishes from sibling 'variant' by being region-based. However, it could explicitly state the action.

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?

Only a size recommendation (≤25kb) is given. No guidance on when to use vs alternatives like 'variant' or 'gene', and no when-not-to-use 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?

Discloses persistence behavior (authenticated vs anonymous sessions, 24-hour retention), which is 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?

Front-loaded with action and purpose; slightly wordy but well-structured and informative.

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?

Covers storage mechanism, scoping, persistence, and retrieval hints; complete for a simple write 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 coverage is 100% with good descriptions; description adds usage context but no essential new info beyond 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?

Clearly states the tool saves data for reuse, specifies key-value storage, and distinguishes from siblings recall and forget.

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?

Explicitly says when to use ('when you discover something worth carrying forward'), gives examples, and pairs with recall/forget.

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 (readOnlyHint: true, destructiveHint: false) align with the description, which adds that the tool returns IDs plus pipeworx:// citation URIs. No contradictions; the description usefully expands on what the agent can expect.

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 concise (3-4 sentences) with the main action in the first sentence. Every sentence serves a purpose: stating function, use cases, examples, and outcome. No unnecessary 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?

Given no output schema, the description adequately explains the return (IDs + citation URIs) and provides examples. It could mention whether partial matches are returned, but overall it's sufficient for an agent to use effectively.

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 descriptions for both parameters. The description adds valuable context, such as acceptable input formats (ticker, CIK, name for company; brand or generic name for drug) and examples, going 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 explicitly states the tool's purpose: 'Look up the canonical/official identifier for a company or drug.' It lists specific identifier systems (CIK, ticker, RxCUI, LEI) and provides clear examples, distinguishing it from siblings like entity_profile.

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 advises when to use the tool: 'Use when a user mentions a name and you need the CIK...' and 'Use this BEFORE calling other tools that need official identifiers.' It also notes it replaces 2–3 lookup calls. However, it does not explicitly state when not to use it.

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 'autocomplete' context beyond annotations (readOnlyHint, openWorldHint), hinting at partial matching and suggestions. However, it lacks details on rate limits, pagination, or response format.

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 wasted words. It efficiently communicates the core 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 tool with one parameter and no output schema, the description is adequate but could specify what the response contains (list of suggestions, IDs, etc.). It does not fully cover the output behavior.

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 0%, but the description clarifies that 'query' is a gene or variant term. This adds some meaning, though format expectations (e.g., HGVS, gene symbols) are not specified.

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 'Gene / variant search (autocomplete)' clearly states the tool's purpose: to search for genes or variants with autocomplete functionality. It effectively distinguishes from sibling tools like 'gene' or 'variant' that likely return full records.

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 minimal guidance on when to use this tool versus alternatives. While 'autocomplete' implies real-time suggestion use, there is no explicit statement of when to prefer this over 'search_entity' or other search 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?

Annotations indicate readOnlyHint=true and destructiveHint=false, so the description should add behavioral context beyond that. It does not mention return type, data scope, or any side effects.

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?

Three words is under-specified, not efficiently informative. Every sentence should earn its place; this one fails to convey essential 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?

Given lack of output schema and minimal description, the tool is insufficiently documented. Sibling tools suggest a retrieval function, but the description fails to clarify what is returned.

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?

With 50% schema description coverage (only transcript_id has a description), the tool description should compensate by explaining parameters. 'Transcript + variants' adds no 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?

Description 'Transcript + variants' is vague and tautological, barely extending the tool name without specifying an action (e.g., retrieve, search). It does not distinguish this tool from siblings like 'gene' or 'variant'.

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 (e.g., 'variant' for variants only, 'gene' for genes). No context on prerequisites 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?

Annotations already declare readOnlyHint=true and destructiveHint=false, so the agent knows it's safe. The description adds value by disclosing the limitation to company-financial claims, explaining the process (NL parsing to numeric comparison), and the return format with a citation and delta.

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 concise, front-loaded with purpose, and includes examples and details in a structured manner without unnecessary 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 single-parameter tool with no output schema, the description covers the main aspects: claim types, verdict set, and replacement of multiple steps. It could mention error handling or unsupported claims, but overall it is sufficiently 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%, with a clear description for the sole parameter 'claim'. The description's examples add some context but do not significantly enhance understanding beyond the schema. 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 the tool's purpose: fact-check, verify, validate claims against authoritative sources. It specifies the type of claims (company-financial) and the verdict types returned. It distinguishes itself from siblings like search or entity_profile by being specialized for claim verification.

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 explicitly says when to use the tool ('when an agent needs to check whether something a user said is true') and gives examples. It also notes the scope (v1 supports company-financial claims) but does not explicitly state when not to use it or mention alternative 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 annotations already indicate the tool is read-only and non-destructive. The description adds no further behavioral details, such as rate limits or data freshness. Since annotations cover the safety profile, the description is adequate but does not go beyond what is already structured.

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 that is front-loaded with the core concept. While concise, it could include a bit more detail without harming clarity. Still, it avoids unnecessary words and is easy to parse.

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 no output schema, the description should hint at what the tool returns. It does not. Additionally, the tool has two parameters, but only one is described in the schema; the description does not compensate. This makes the tool less usable without external documentation.

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 has 50% description coverage (only 'dataset' has a description). The tool description does not explain the parameters further; for instance, it doesn't define the 'variant_id' format beyond the example, nor does it list valid datasets. These gaps reduce the agent's ability to use parameters correctly.

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 retrieves a variant by chromosome-position-ref-alt or rsid. It provides an example for the expected format, making it easy to understand. It distinguishes itself from sibling tools like 'gene' or 'region' which operate on different identifiers.

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 when to use the tool (when you have a variant identifier), but it does not explicitly state when not to use it or mention alternative tools. Given the siblings include 'gene' and 'region', more explicit guidance would help, but the context is clear enough for an informed agent.

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