Simbad

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

Annotations already declare readOnly and openWorld hints. The description adds that it routes to multiple tools, fills arguments, and returns structured answers with citation URIs. It doesn't contradict annotations and provides useful behavioral context beyond the metadata.

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 moderately long but well-structured: it starts with a priority directive, lists supported data types, explains the mechanism, and ends with usage triggers and examples. Every sentence adds value, though minor trimming could be possible.

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 one parameter and no output schema, the description is quite complete. It explains what the tool does, when to use it, the nature of the answer (structured with citations), and provides many examples. It lacks output format details but is sufficient for agent usage.

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 only parameter 'question' is described in the schema as natural language. The tool description enriches this by specifying the types of questions (factual, current/historical data) and giving examples, adding value beyond the schema's minimal 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 clearly states the tool's purpose: it answers factual questions using structured data from numerous verified sources, with examples and a list of domains. It distinguishes itself from web search and other tools by emphasizing authoritative data and citations.

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 prefers this tool over web search for factual queries and provides concrete triggers like 'what is', 'look up', 'find', etc. It lists applicable domains and implies not to use for non-factual questions, offering excellent usage 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?

Annotations already declare readOnlyHint=true and openWorldHint=true, which describe safety and world access. The description adds behavioral details: it resolves markets, classifies bets, fans out to packs (e.g., crypto+fred+gdelt for BTC), and returns an evidence packet with market-vs-model comparison. 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 relatively long (three sentences plus a marketing sentence). It front-loads the main purpose but includes some extraneous detail (e.g., 'This is the core demo product — agents that get bet-relevant context here convert better'). While informative, it could be 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?

Given the complexity of the tool (multiple input types, fan-out logic, classification), the description covers the key points: input, processing steps, and output (evidence packet plus comparison). Without an output schema, the description explains the return value adequately, though not exhaustively.

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 meaning beyond the schema: it explains that 'market' accepts slug, URL, or question text, and 'depth' has defaults ('quick' vs 'thorough'). This adds value over the schema alone, so score is above 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 clearly states the tool researches a Polymarket bet by pulling relevant Pipeworx data. It specifies input types (slug, URL, question text) and exactly what it does: resolve market, classify bet, fan out to packs, return evidence packet and comparison. This distinguishes it from siblings like polymarket_edges or validate_claim.

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 use cases: 'should I bet on X?', 'what does the data say about this Polymarket market?', 'is there edge in this bet?'. It tells the agent when to invoke this tool. However, it does not mention alternatives or when not to use it, slightly lowering the score from 5.

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, and destructiveHint=false, making it clear this is a safe read operation. The description adds behavioral context: it pulls from external sources, returns paired data with citation URIs, and replaces 8–15 sequential calls. 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?

The description is a single paragraph but front-loaded with the purpose, each sentence adds value (use cases, data sources, performance benefit), and is appropriately sized for a tool that does two different things.

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 complexity, the 100% schema coverage, and annotations that provide safety and open-world context, the description is complete. It mentions return format (paired data + citation URIs) and performance benefit, compensating for the lack of 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 coverage is 100%, so baseline is 3. The description adds significant meaning beyond the schema by explaining that type='company' pulls financial data from SEC EDGAR for tickers/CIKs, while type='drug' pulls adverse events/approvals/trials. It also clarifies that values should be tickers for company or drug names for drugs.

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 compares 2–5 companies or drugs side by side, specifying data sources (SEC EDGAR, FAERS, FDA, trials) and concrete use cases. It distinguishes from siblings like entity_profile by focusing on side-by-side 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 provides explicit when-to-use cues with example user phrases ('compare X and Y', 'X vs Y', 'stack up', 'which is bigger') and mentions the types. It lacks explicit alternatives for when not to use, but the context is clear enough.

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 description adds limited value by specifying that results are objects within a radius. It does not disclose pagination behavior, coordinate frame, or return format, which are gaps 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?

The description is a single, front-loaded sentence with no extraneous words. It efficiently conveys the core function, earning its place without wasted space.

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 doesn't explain return format or result interpretation. For a simple cone search, it's minimally adequate but lacks details like coordinate system, result ordering, or error cases that a complete tool definition should provide.

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 description coverage (only 'max' described), the tool description adds no parameter-specific details beyond the schema. It fails to explain 'ra,' 'dec,' and 'radius_deg' semantics, leaving the agent with minimal guidance on 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 'Objects within a radius of (RA, Dec) decimal degrees' clearly specifies the tool's function as a positional cone search in astronomical coordinates. While it uses a weak verb 'within,' the name 'cone_search' reinforces the purpose, and it is distinguishable from sibling tools like 'object' (likely single-object lookup).

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 or when not to use this tool versus alternatives. The description does not mention prerequisites, coordinate system details, or compare with siblings like 'resolve_entity' or 'object,' leaving the agent to infer 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?

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds that it returns 'top-N most relevant tools with names + descriptions', which clarifies the output behavior beyond annotations. 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?

The description is well-structured, front-loaded with purpose, and includes a helpful list of domains. It could be slightly more concise by reducing the domain list length, but overall it is clear and 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 adequately explains the return (tool names and descriptions) and the top-N behavior. It provides sufficient context for a meta-tool that searches other tools, though it omits details like result 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?

Schema coverage is 100% with descriptions for both parameters. The description references 'natural language description' matching the query param, and 'top-N' implies the limit parameter, but adds minimal additional meaning. 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 'Find tools by describing the data or task' and provides specific domains (SEC filings, financials, etc.). It explicitly distinguishes itself from siblings by advising 'Call this FIRST' to see the option set, making its purpose and uniqueness very 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 provides clear when-to-use guidance: 'Use when you need to browse, search, look up, or discover what tools exist for...' and explicitly recommends calling it FIRST. It does not explicitly mention when not to use it or list alternatives, but the guidance is strong enough.

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, but the description adds significant behavioral context: it returns recent SEC filings, financials, patents, news, and LEI with citation URIs. It also notes that names are not supported. 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 five sentences, each serving a purpose. It is front-loaded with the main purpose, then gives usage examples, then details of returns, and finally input constraints. 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?

Given the tool's complexity (aggregating data from multiple sources), the description is complete. It lists the types of data returned, acceptable inputs, and what not to do. No output schema exists, but the description adequately covers return content.

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?

Both parameters are described in the schema with 100% coverage. The description adds additional context: type is currently only 'company', and value can be a ticker or zero-padded CIK, with explicit note that names are not supported. This enriches the schema 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 clearly states the tool's purpose: 'Get everything about a company in one call.' It specifies the verb 'get' and resource 'everything about a company', and distinguishes from siblings by mentioning it replaces calling 10+ pack tools across multiple domains.

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 example queries like 'tell me about X' and 'research Microsoft', and gives guidance on when to use it. It also explains what to do if only a name is available: use resolve_entity first. This is clear and actionable.

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, so the destructive nature is known. The description adds context about clearing sensitive data and stale context, which adds value beyond annotations but does not introduce new behavioral 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 two sentences, with the core action in the first sentence and usage guidance in the second. No wasted words; efficiently communicates purpose and context.

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 deletion tool with one parameter and no output schema, the description covers when and why to use it. It mentions pairing with siblings for completeness. Minor gap: does not specify return behavior or error handling, but this is acceptable given 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 coverage is 100% with a clear description for the 'key' parameter. The description only mentions 'by key', adding no extra semantics 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 description clearly states the tool deletes a previously stored memory by key, using specific verb 'Delete' and resource 'memory'. It distinguishes from siblings by mentioning 'remember' and 'recall'.

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 tells when to use the tool: 'when context is stale, the task is done, or you want to clear sensitive data'. It pairs with siblings but doesn't explicitly state when not to use, though the context is sufficient.

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 readOnlyHint and destructiveHint false, so the description's mention of 'fetch' aligns with a read operation, adding no further behavioral disclosure. No details on error handling, response format, or potential side effects (even though destructiveHint is false). The description adds minimal value 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?

The description consists of a single concise sentence with no unnecessary words. It is front-loaded and efficiently conveys the core purpose and parameter usage via examples.

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 functional but incomplete. It explains the parameter but omits information about the return value, error cases, and any constraints. With 0% schema description coverage and no output schema, additional context would be beneficial.

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%, so the description must clarify parameter meaning. It explains that 'identifier' is an object identifier with examples ('M31', 'HD 209458'), which helps. However, it does not specify allowed formats, case sensitivity, or expected pattern. Given only one parameter, the description provides some context but is not fully detailed.

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 action (resolve and fetch) and the target (basic record for an object identifier). It includes concrete examples (e.g., 'M31', 'HD 209458'). However, it does not distinguish from a sibling tool 'resolve_entity' that may serve a similar purpose.

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 is no mention of prerequisites, limitations, or exclusion criteria. The description simply states the action without context for appropriate use.

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?

Describes behavioral traits beyond annotations: rate-limited to 5 per identifier per day, free, doesn't count against tool-call quota, team reads digests daily, signal affects roadmap. No contradiction with annotations (readOnlyHint=false, destructiveHint=false).

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 well-structured: starts with purpose, then usage guidance, then constraints. All sentences are necessary and add value. It is appropriately sized for the tool's complexity.

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 explains what happens after submission (team reads digests, affects roadmap). It also covers limitations (rate limit, free usage). For a feedback tool, this 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 descriptions. The description adds value by explaining the usage context for 'type' and providing formatting guidance for 'message' (be specific, 1-2 sentences, 2000 chars max). The 'context' parameter is explained with examples ('pack slug', 'tool name', 'vertical'). This goes beyond the schema definitions.

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 is for providing feedback to the Pipeworx team, specifying categories like bug, feature/data_gap, and praise. It distinguishes itself from sibling tools which are for querying, betting, searching, etc., so it stands alone.

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 when to use ('when a tool returns wrong/stale data', 'when a tool you wish existed isn't in the catalog', 'when something worked surprisingly well'). Also provides guidance on how to write feedback (describe in terms of Pipeworx tools/packs, don't paste end-user prompt). Mentions rate limit and free 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?

Annotations already declare readOnlyHint=true and openWorldHint=true. The description adds behavioral context: it walks child markets, groups related markets, and checks monotonicity. It explains the search behavior in topic mode and clarifies the return includes ranked opportunities with trade direction and reasoning. 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 well-structured with a clear main purpose, then two mode explanations with examples. It front-loads the key verb ('Find arbitrage opportunities') and uses bullet-like formatting for modes. Could be slightly more concise in the example parts, but overall 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 adequately explains the return format (ranked opportunities with suggested trade direction and reasoning). It covers both modes, the logic (monotonicity violations), and the problem it solves (separate events for different deadlines). No missing 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?

The input schema has 100% coverage with descriptions for both parameters. The description adds significant value by explaining the two modes and how each parameter triggers a different behavior (event vs topic), and provides examples like event slug format and topic seed question. This goes well beyond the schema definitions.

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 by checking monotonicity violations across Polymarket markets. It specifies two distinct modes (event and topic) and explains what each does, distinguishing it from sibling tools like 'validate_claim' or 'bet_research' which serve different purposes.

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 explicit guidance on when to use each mode: event mode for a single Polymarket event slug, topic mode for cross-event searches using a seed question. It explains why cross-event mode is needed for cases where Polymarket lists each deadline as a separate event, preventing misses from single-event mode. However, it doesn't explicitly state when not to use the tool or provide alternatives.

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 details the model (lognormal from FRED + coinpaprika), process (scans top markets, groups by asset, fetches price history once, computes probability, ranks by edge), and output (top N with trade direction). Annotations (readOnlyHint=true, destructiveHint=false) are consistent, and the description adds significant behavioral context 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 paragraph that effectively front-loads the purpose and then provides detail. It is informative but could be slightly more concise; however, it uses every sentence to add 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?

Given the tool has no output schema, the description adequately describes the output (top N with trade direction). All three parameters are explained, annotations are present, and the description covers the algorithm and purpose fully for its 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% with descriptions, but the tool description adds default values (limit default 10, window default 1wk, min_edge_pp default 0.5) and clarifies max value for limit (max 25), providing additional 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 description clearly states the tool scans high-volume Polymarket markets, identifies where Pipeworz data disagrees with market price, and returns top edges ranked by magnitude with suggested trade direction. It distinguishes itself from siblings like polymarket_arbitrage by focusing on disagreement edges for betting opportunities.

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 the tool is built for the 'what should I bet on today' question, implying usage when discovering opportunities. It doesn't explicitly state when not to use or mention alternatives, but the context of sibling tools provides some 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 value beyond annotations by explaining the scope (per identifier) and the behavior when omitting the key. It is consistent with readOnlyHint and destructiveHint, with 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?

The description is two sentences, front-loaded with the core action, and every sentence adds necessary context 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?

For a simple tool with one parameter and no output schema, the description fully covers input behavior, scope, and related actions ('remember', 'forget'), leaving no gaps.

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 reiterates the same information (omit key to list). It does not add new semantic detail beyond the schema, earning a baseline score 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 clearly states the tool retrieves a stored value via 'remember' or lists all keys by omitting the key argument, distinguishing it from siblings like 'remember' 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?

The description provides explicit use cases (retrieving target ticker, address, notes) and mentions pairing with 'remember' and 'forget', offering good context for when to use this tool, though no explicit 'when-not' 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?

Annotations already indicate read-only and non-destructive behavior. The description adds context about parallel fan-out across three sources and the return format (structured changes, total_changes, citation URIs), which enhances transparency 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?

The description is concise and well-structured: it starts with the core purpose, lists example queries, explains backend sources, parameter details, and return format. Every sentence adds value with no 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?

Despite lacking an output schema, the description adequately explains the return value (structured changes + count + URIs) and covers all key aspects: use cases, parameter formats, and backend behavior. It is sufficiently complete for an agent to understand and 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?

All parameters have descriptions in the schema (100% coverage), so baseline is 3. The description adds valuable examples for the 'since' parameter (e.g., '7d', '30d', '1y') and clarifies the 'value' parameter can be a ticker or CIK, which goes beyond schema 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 purpose: monitoring recent changes for a company. It provides specific example queries and distinguishes from sibling tools by detailing its backend sources (SEC EDGAR, GDELT, USPTO).

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 use cases are given (e.g., 'what's happening with X?', 'any updates on Y?'), providing clear guidance on when to invoke. However, it does not explicitly contrast with sibling tools or mention when not to use this 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?

Annotations indicate readOnlyHint=false and destructiveHint=false. The description adds context about scoping by identifier, authentication persistence, and 24-hour retention for anonymous sessions. 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 dense paragraph without wasted words. It efficiently conveys essential information, though it could be slightly more structured for readability.

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 key aspects but omits return value or confirmation behavior. For a simple store tool, it is adequate but could be more complete regarding success/error indications.

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%, but the description adds examples for key ('subject_property') and notes that value can be any text, which enhances understanding beyond the schema's descriptions.

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: 'Save data the agent will need to reuse later'. It specifies the resource (key-value memory) and distinguishes from siblings like recall and forget, which have different actions.

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 explicitly advises when to use: 'when you discover something worth carrying forward' and pairs with recall and forget. It also discusses scoping and retention policies, providing clear context for use.

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 tool is safe. The description adds value by stating it returns IDs plus pipeworx:// citation URIs, and notes that it replaces multiple lookups. No contradictions with annotations. It could mention rate limits or failure modes, but current detail is sufficient.

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 paragraph, roughly 4 sentences, with no wasted words. It front-loads the core purpose and then adds examples and usage guidance. Could be slightly shorter, but the content justifies its length.

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 has 2 required parameters and no output schema. The description explains return values (IDs + citation URIs) and provides examples. It covers the essential behavioral aspects (lookup, multiple ID systems). Could benefit from mentioning error handling or ambiguous matches, but given the simplicity, it is adequately 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 descriptions for both 'type' (enum) and 'value' (freeform). The description enhances parameters by providing examples (e.g., 'AAPL', '0000320193', 'ozempic') and clarifying the identifier systems returned. This adds meaning beyond the schema's basic parameter descriptions.

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 'look up' and the resource 'canonical/official identifier for a company or drug'. It specifies identifier types (CIK, ticker, RxCUI, LEI) and gives concrete examples ('Apple' → AAPL/CIK, 'Ozempic' → RxCUI). This differentiates the tool from siblings like entity_profile or compare_entities, which serve different purposes.

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 'Use when a user mentions a name and you need the CIK... the ID systems that other tools require as input' and 'Use this BEFORE calling other tools that need official identifiers'. This provides both context and ordering, making it clear when and how to invoke the 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?

Annotations declare readOnlyHint, openWorldHint, destructiveHint, making the tool's safety profile clear. The description adds a link to full documentation but no additional behavioral traits like return format or 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?

Extremely short (one sentence). While concise, it lacks sufficient detail for an AI agent to use the tool correctly, especially given the external link reliance.

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 required string parameter, no output schema, and only annotations for safety, the description should explain the parameter format and expected output. It fails to do so, making the tool's usage unclear.

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 'script' has no description in the schema (0% coverage) and the tool description does not explain what the string should contain (e.g., commands, file reference). The external link may help, but the description itself adds no 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?

Clearly states the tool runs a SIMBAD sim-script, which is a specific action on a specific resource. However, it does not distinguish from siblings like 'tap' or 'ask_pipeworx' that might also execute 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?

No guidance on when to use this tool versus alternatives, e.g., 'tap'. The external link provides documentation but the description itself offers no 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?

Annotations already declare readOnlyHint=true, openWorldHint=true, and destructiveHint=false. The description adds that the query is synchronous and defaults to JSON output, which is useful but not extensive. 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 a single concise sentence that conveys the essential information. It is front-loaded with the main action and resource. While very brief, it contains 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 the simplicity (2 params, no output schema, annotations present), the description is minimally adequate but lacks context on output structure, error behavior, or relationship to sibling query tools. It does not fully enable an agent to use the tool without additional knowledge.

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 description adds no new parameter meaning beyond the schema. The mention of 'JSON by default' repeats the schema's default for 'format'. 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 specifies the action (ADQL TAP query), resource (SIMBAD database), and key details (sync, default JSON return). It is specific enough to distinguish from unrelated tools but does not explicitly differentiate from the sibling 'cone_search' which may also involve 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?

No guidance is provided on when to use this tool versus alternatives like 'cone_search' or other query tools. The description only states what it does, not the recommended context or 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?

Adds valuable context beyond annotations: returns verdict types, structured form, actual value with citation, and delta. Mentions sources (SEC EDGAR + XBRL) and that it combines multiple steps. Consistent with readOnlyHint and openWorldHint.

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 concise paragraphs: first covers purpose/usage, second covers technical details. Every sentence adds value; no 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?

For a tool with one parameter and no output schema, description covers purpose, usage, return values, limitations (v1 scope), and provides example claims. Fully 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 has 100% coverage with description of 'claim' parameter. Description adds example claims and notes supported claim types, enhancing understanding 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 fact-checks natural-language claims against authoritative sources, with specific verb+resource (validate_claim). Distinguishes from siblings by noting it replaces 4-6 sequential 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?

Explicitly says when to use (to check truth of user statements) and gives example queries. Scope limited to company-financial claims, but does not contrast with sibling tools like bet_research or cone_search.

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