Cdec Ca

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

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint. The description adds important behavioral details: the default model and cost model (free vs. BYO key), that _apiKey is passed directly to Anthropic, and that the response includes per-model raw data and a combined view. 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 compact (4 sentences) and front-loaded with the core action. Every sentence adds value: purpose, default behavior, optional key, return format, use cases. No unnecessary repetition.

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 fully explains the return format (per-model score, confidence, signals, raw_response + combined view). It covers the required parameter, optional parameters, and use context. The tool's complexity is well-addressed, and annotations further fill safety profile.

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

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

Schema description coverage is 100%, so the schema already documents parameter meaning. The description adds some context (default model, BYO key usage) but does not significantly extend individual parameter semantics beyond what the schema provides. 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 verb 'Probe' and the resource 'one or more LLMs', specifies the output 'score visibility (0-100) per model', and gives concrete use cases (AI-marketing audits, pre-launch checks, competitive monitoring). It distinguishes itself from sibling tools like scan_competitor_ai_presence or compare_entities by focusing on LLMs' knowledge of a specific 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?

The description provides explicit contexts for use (marketing audits, brand checks, monitoring) and clarifies when to provide an API key for Anthropic versus using the free default. It does not explicitly state when not to use or list alternatives, but the given guidance is sufficient for a typical agent.

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

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

Annotations already declare readOnlyHint, openWorldHint, etc. Description adds substantial behavioral context: routes to 4,552 tools, fills arguments, returns structured answers with citation URIs. 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 comprehensive but well-structured, with front-loaded purpose, explicit usage guidelines, and concrete examples. Every sentence adds value 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 complex tool with no output schema, the description gives a good sense of capabilities and scale (4,552 tools, 1,160 sources). It mentions citations but could be more explicit about the return format. Still largely 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 has 6 parameters (question plus 5 aliases) with 100% description coverage. The description does not add extra meaning beyond what the schema provides; it mentions 'fills arguments' but no additional parameter details. 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: routing questions about structured data to over 4,500 tools. It uses specific verbs ('ask', 'routes', 'returns') and differentiates from siblings by explicitly preferring this over web search and naming alternatives like ask_pipeworx_grounded and deep_research.

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 guidance (prefer over web search, start here), examples of appropriate questions, and when to step up to other tools (grounded or deep research). Also notes it works on every tier and is one fast call.

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 the full behavior: routing, extraction, return schema (answer, evidence, confidence, etc.), refusal reasons, and extra LLM call cost. Annotations already indicate read-only and idempotent, 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 well-structured with key sections, but slightly verbose (e.g., detailed return schema could be shortened). Still, no wasted sentences.

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

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

For a tool with no output schema, the description provides a very detailed return structure and behavioral context covering success and failure modes. Differentiates well from siblings.

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?

Description notes that question accepts aliases, but all parameters are already documented in the schema with 100% coverage. No additional meaningful semantics beyond what 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 extracts answers from tool results using only the data, with evidence and refusal reasons. It distinguishes from ask_pipeworx by highlighting groundedness and hallucination-resistance.

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 advises use for high-stakes reads where answers will be quoted or acted on, and recommends ask_pipeworx for casual lookups. Mentions cost tradeoff.

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 extensive behavioral details: how the tool resolves markets, fan-out to specific data sources, response shapes, edge cases (low confidence, closed markets), resolution-rule risk, and news fallback behavior. Annotations already indicate readOnly and idempotent, and the description adds significant context 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 very long and dense, containing many details. While it is front-loaded with purpose and well-organized with sections, it is not concise; every sentence earns its place but could be trimmed for brevity.

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

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

Given the tool's complexity (3 parameters, no output schema), the description comprehensively covers input resolution, fan-out logic, response fields, error cases, and safety notes, 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 coverage is 100%, so baseline 3. The description adds value by providing examples of market input (slug, URL, question text), explaining depth enum meanings, and clarifying the include_raw default and use cases for true/false.

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 it researches a Polymarket bet by pulling relevant Pipeworx data, lists classifiers, fan-out examples, and response shapes, clearly distinguishing it from sibling tools like polymarket_edges or polymarket_arbitrage.

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 usage scenarios ('should I bet on X', 'what does the data say about Y'), safety warnings (low-confidence matches, closed markets, wide spreads), and advice on inspecting market_match_confidence before trusting analysis, as well as guidance on the include_raw parameter.

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

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

The description adds significant behavioral context beyond annotations: it reveals data sources (SEC EDGAR/XBRL for companies, FAERS for drugs), handling of off-calendar fiscal years, sorting by primary metric, and citation URIs. No contradiction with annotations (readOnlyHint, etc.).

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 key query patterns and uses a structured format with examples. It is relatively long but every sentence adds value, justifying its length for the 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?

Despite no output schema, the description covers data sources, sorting, output format (paired data + citation URIs), and both entity types comprehensively. It is complete for the 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 coverage is 100% (both parameters described). The description enriches semantics by explaining what each type pulls (financials vs. adverse events), and provides examples for values (tickers/CIKs for companies, drug names). Adds substantial meaning.

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

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

The description clearly states the tool performs side-by-side comparison of 2-5 companies or drugs in one call. It includes specific user query examples ('X vs Y', 'rank these companies') and explicitly says it replaces 8-15 sequential lookups, 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 explicitly says 'ALWAYS PREFER over sequential single-pack lookups when comparing entities,' providing strong when-to-use guidance. It does not explicitly list when-not-to-use or alternatives, but the context of sibling tools implies entity_profile for single entities.

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, idempotentHint, destructiveHint=false. The description adds no additional behavioral context, but annotations cover the safety profile, so minimal credit applies.

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

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

The description is extremely short (6 words) but lacks essential details, making it under-specified rather than concise. Every sentence should add value, but here it is insufficient.

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 an output schema existing, the description is incomplete: it does not explain the tool's scope, how parameters interact, or what data is returned. Given the complexity (4 params, 3 required) and many siblings, more information is needed.

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 25% (only start has description 'YYYY-MM-DD'). The description does not elaborate on parameters beyond mentioning 'station, sensor' in a parenthetical, leaving end and semantics of sensor/station_id unclear.

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 'Daily data for (station, sensor).' is vague; it does not specify the verb (retrieve, list) or differentiate from siblings like hourly_data or event_data.

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

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

No guidance on when to use this tool vs alternatives (e.g., hourly_data, event_data). The description does not mention any context or exclusion criteria.

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

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

Discloses account requirements, parallel decomposition, return format (findings packet with gaps), limitation for non-structured topics, and execution time. Complements existing annotations 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?

Well-structured with critical info front-loaded (account requirement). Slightly lengthy but every sentence adds value; could be tightened slightly.

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?

Comprehensive despite no output schema: explains return format, gaps, expected time, authentication, limitations, and alternatives. Addresses all likely agent needs for selection and invocation.

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

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

Adds meaning beyond schema: explains depth enum values map to facet counts (quick=3, standard=5, thorough=8) and notes 'thorough' requires paid plan. For question parameter, clarifies natural language and suitability for broad questions.

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 performs grounded multi-source research across 1160 structured data sources, distinguishes from sibling tools like ask_pipeworx, and explicitly says it is not open-web 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?

Provides explicit when-to-use (broad/multi-part questions over structured data) and when-not-to-use (single lookup, breaking news) with named alternatives (ask_pipeworx).

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, idempotentHint=true, destructiveHint=false. The description adds valuable behavioral context: 'Returns the top-N most relevant tools with names, descriptions, and full input schemas (with curated examples) — each result is ready to call directly, no second schema lookup needed.' 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-organized: opens with purpose, then usage, then what is returned. While slightly long, it's concise given the complexity. Every sentence adds value. Could be slightly tighter, but still good.

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 fully explains return values: 'top-N most relevant tools with names, descriptions, and full input schemas (with curated examples) — each result is ready to call directly.' It also covers the limit parameter behavior. Complete for a discovery 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%, so baseline is 3. The description provides examples and explains that 'query' accepts natural language and lists aliases, but the schema already documents these. The description adds marginal value beyond schema for parameters.

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: 'Find tools by describing the data or task.' It lists many example domains (SEC filings, financials, FDA, etc.), distinguishing it from sibling tools which are specific. The verb 'discover' and resource 'tools' make it highly specific.

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 guides when to use: 'Call this FIRST when you have many tools available and want to see the option set (not just one answer).' It also provides usage scenarios like 'browse, search, look up, or discover what tools exist for...' This fully satisfies the usage guidelines dimension.

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 behavior: fans across multiple sources, returns specific fields, notes a soft-failure for patents, and all traits match annotations (read-only, idempotent, 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 a single dense paragraph that efficiently conveys all necessary information without redundancy, though it is slightly long due to 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?

The description fully explains the output structure with examples of fields returned, covers limitations (USPTO sunset, name unsupported), and references a sibling tool for missing functionality, making it complete for agent decision-making.

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 context about unsupported name input and the need to use resolve_entity first, 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 clearly states the tool returns a full cross-source profile of a US public company, provides example queries, and differentiates from sibling tools like resolve_entity by explicitly noting when to use each.

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 when to use (holistic view), when not to use (if only a name, use resolve_entity first), and states preference over chaining other 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 already indicate read-only, idempotent, non-destructive. The description adds 'irregular' which provides slight behavioral context (data not at regular intervals). No contradiction; adequate but minimal extra 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?

Extremely concise (one phrase) but at the expense of clarity and completeness. The description is under-specified for a tool with 4 parameters and many siblings.

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

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

Given the complexity (4 params, output schema exists, rich annotations), the description is highly incomplete. It fails to explain what events are, how the tool behaves, or offer examples.

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

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

Schema description coverage is 0%, and the description adds no meaning to the parameters (end, start, sensor, station_id). Without parameter descriptions, the tool is hard to invoke correctly. Output schema exists but does not mitigate this gap.

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 'Event-based irregular data' is vague. It does not state a specific verb (e.g., retrieve, list) or clearly identify the resource. It only hints at the data type (irregular) but lacks distinction from sibling tools beyond that.

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 guidelines on when to use this tool versus alternatives like daily_data or hourly_data. The description does not specify when not to use it or provide context for selection.

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

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

Annotations already provide destructiveHint=true and idempotentHint=true. Description confirms delete operation but adds no new behavioral details beyond annotation. Consistent 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?

Two concise sentences with no filler; first sentence states action, second provides usage guidance.

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?

Simple tool with one parameter; description covers purpose and usage context. Lacks detail on error behavior (e.g., key not found) but acceptable for such a simple 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% and description provides no additional meaning for the 'key' parameter beyond what the schema already states.

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

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

Description states 'Delete a previously stored memory by key' which is a specific verb+resource and distinguishes from siblings '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?

Explicitly lists when to use: 'when context is stale, the task is done, or you want to clear sensitive data'. Mentions pairing with related tools but does not explicitly state when not to 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 idempotentHint=true and readOnlyHint=true. The description adds that the tool fetches the page, extracts content, and emits markdown. This provides behavioral details beyond annotations 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 two sentences: the first delivers the core functionality, the second lists use cases. It is front-loaded, concise, and contains no redundant information.

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

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

The description explains inputs and output (text blob) and provides usage examples. No output schema exists, but the description compensates by describing the return format. Could be slightly richer on output details, but sufficient.

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, describing both 'url' and 'max_links' with clear explanations. The description does not add additional semantics for these parameters, so 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 verb 'generate', the resource 'llms.txt file', and the scope 'for any URL'. It also specifies the target users (AI crawlers) and use cases, distinguishing it from sibling tools which are not about generating llms.txt.

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 lists three concrete use cases: indexing a client's site, drafting for own project, or auditing a competitor. It provides clear context for when to use, though it does not mention when not to use or explicitly contrast with siblings.

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

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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, and openWorldHint=true. The description adds no behavioral context beyond these 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 extremely brief but at the cost of being under-specified. It lacks essential information to guide invocation.

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 (4 parameters, siblings), the description is wholly inadequate. It fails to provide any contextual completeness.

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 0% schema description coverage, the description must explain parameters but does not. It offers no meaning for station_id, sensor, start, or end beyond what examples suggest.

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 'Hourly data.' is a tautology of the tool name. It does not specify a verb or resource, and fails to distinguish from sibling tools like daily_data or event_data.

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. No prerequisites, context, or exclusions are provided.

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

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

Annotations already declare the tool as read-only, idempotent, and non-destructive. The description adds no behavioral detail (e.g., what 'latest' means, how data is sourced, or any constraints). It misses the opportunity to clarify the scope or quality of the returned 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 extremely short, but this is under-specification rather than conciseness. A single phrase fails to earn its place because it conveys no actionable information.

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

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

Given the presence of an output schema and the need to specify what 'latest value' means for sensor/station pairs, the description is completely inadequate. It omits return format, data source, and any behavioral context.

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

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

With 0% schema description coverage, the description must explain the parameters 'sensor' and 'station_id' but instead says nothing. The examples in the schema provide some clues, 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?

The description 'Latest value.' is a tautology that restates the tool name 'latest' without specifying what the value represents or what action the tool performs. It fails to identify the resource (e.g., sensor data) or differentiate from siblings like daily_data or hourly_data.

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. With many data-oriented sibling tools, the absence of usage context leaves the agent without decision support.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is clear. The description adds context about returning only active subscriptions and the optional include_inactive parameter, 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 two sentences, front-loaded with the main action and outcome, and includes concrete use cases. Every sentence adds value 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?

Given the annotations (readOnly, idempotent, not destructive) and simple input schema (one optional boolean), the description sufficiently covers what the tool does, what it returns, and why it should be used. No output schema exists, but the description lists output fields.

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

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

Schema coverage is 100%, so the schema already explains the single optional parameter (include_inactive) with its description. The tool description does not add any additional meaning beyond what the schema provides, hence 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 lists the caller's active subscriptions and specifies the returned fields (id, type, params, etc.). It distinguishes from sibling tools like subscribe and unsubscribe by its listing and querying 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?

The description explicitly advises when to use: to review what you're monitoring before adding more subscriptions or to find an id to cancel. This provides clear context, though it doesn't 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?

Annotations indicate not read-only and not destructive. Description adds that it's free and doesn't count against tool-call quota, plus rate limits. 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?

A single paragraph that efficiently conveys purpose, usage, tips, and limitations. Every sentence adds value 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 feedback tool, the description covers all necessary information: when to use, how to format, limitations, and impact. No output schema needed.

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 tool description adds extra guidance on how to write the message (specific, length) and explains the enum values in 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 the tool's purpose: sending feedback about bugs, features, data gaps, or praise. It distinguishes itself from sibling tools (which are mostly data retrieval) by being a communication channel.

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 specifies when to use each feedback type (bug, feature, etc.) and provides a 'don't paste end-user prompt' rule. Also mentions rate limits and quota-free nature.

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 safe, read-only, idempotent behavior. Description adds valuable context: self-aggregating signal from CF analytics-engine, no PII, caching duration (5min-1h). 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?

Concise at 6 sentences with numbered use cases, front-loaded core purpose, no extraneous text.

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

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

For a simple, read-only tool with one parameter and no output schema, the description thoroughly covers purpose, usage, behavior, data source, and caching, 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?

Only parameter 'window' has enum and schema description; the tool's description adds nuanced guidance on short vs. long windows, enhancing 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?

Clearly states the tool returns top tools, packs, and call volume over a window. Lists specific use cases, distinguishing it from sibling tools like discover_tools or daily_data by focusing on what other AI agents are calling.

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 three explicit use-case scenarios and explains window option implications. Could briefly mention alternatives, but the guidance 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 declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds substantial behavioral context: details on semantic anchor (Jaccard similarity), partition filter (placeholder slugs), fill check (CLOB depth analysis), and when not to trade. No contradictions with annotations; instead, it enriches the agent's understanding of the tool's internal logic.

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 dense but well-organized, using clear labels like 'SEMANTIC ANCHOR', 'PARTITION FILTER', 'FILL CHECK'. It front-loads the purpose and usage. Every sentence adds information, though minor condensation could be possible. Overall, efficient for the 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 the tool's complexity (2 params, no output schema, sophisticated internal logic), the description is remarkably complete. It explains input modes, internal checks, output format (opportunities array with fields), and how to interpret results (realizable_edge_pp ≤ 0 means no trade). It also references a sibling tool for custom sizing, covering the agent's needs.

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?

Input schema has 100% coverage with descriptions for both parameters, so baseline is 3. The description adds value beyond schema by explaining the format (event slug, full URLs accepted), recommending event mode, and describing the behavior difference between modes. This extra context justifies a score above baseline.

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

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

The description clearly states the tool's purpose: 'Find arbitrage opportunities on Polymarket via monotonicity violations + partition-sum checks.' It specifies the verb (find), resource (arbitrage opportunities), and methodology. It also distinguishes between three modes (no args, event, topic), differentiating it from sibling tools like polymarket_edges.

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 guidance on when to use each mode: 'Call with NO args for a trending_scan... pass event for... or topic for...'. It recommends event mode for specific markets and explains cross-event mode's advantage. It mentions custom sizing using polymarket_fill_risk, but does not explicitly exclude when to use other sibling tools like polymarket_edges.

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 goes far beyond the annotations (readOnly, openWorld, idempotent, non-destructive) by detailing internal logic (three segments with specific formulas), response structure (by_segment, diagnostics), caching behavior (1h KV), and the meaning of all returned fields. It fully discloses what the tool does and how it behaves.

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 information-dense and logically organized (purpose, segments, output fields, knobs, top-level response), but it is verbose and could be more concise. Some technical details (e.g., specific Greek letters) might be simplified.

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 (9 parameters, no output schema), the description is exceptionally complete. It explains all output fields, diagnostics for empty segments, caching, and usage knobs. An agent has everything needed to invoke and interpret results without additional 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?

Although the input schema already covers all 9 parameters with descriptions, the tool description adds significant context: e.g., explains that min_kelly filters small opportunities, slippage_pp accounts for Polymarket's bid/ask depth, and min_partition_leg_kelly targets per-leg Kelly inside partitions. This adds 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's purpose: 'Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price.' It explicitly targets the 'what should I bet on today' use case and distinguishes from siblings like 'polymarket_arbitrage' by focusing on edge discovery across three model families.

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 on when to use the tool (opportunity discovery) and includes usage notes like 'Fed bets surface here, excluded from ranking' and that it's cached. However, it does not explicitly state when not to use it or provide direct comparisons to alternatives like 'polymarket_arbitrage'.

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 goes far beyond the readOnlyHint annotation by detailing response structure (tracked, expired, snapshot_dates), snapshot behavior (written on cache-miss, gaps mean no scan), computation (decay from daily closes, not intraday), and limitations. 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 dense and front-loaded with key purpose, then structured RESPONSE section. While lengthy, every sentence adds value. Could be slightly more concise by separating sections more explicitly, but effective overall.

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 fully explains the return structure (tracked, expired, snapshot_dates) with details on fields like trend, decay_pp_per_day, lifespan_days. It covers limitations and caveats, making it complete for an agent.

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 (days, window) are described in the schema with 100% coverage. The description adds context like default and max for days, and default window family, enriching understanding beyond 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's purpose: 'Edge persistence and decay telemetry' that answers 'how long has this edge existed and is it shrinking?'. It distinguishes itself from sibling tools like polymarket_edges by focusing on temporal persistence.

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 context on when to use the tool, e.g., distinguishing between fresh and old edges ('a fresh wide edge and a 3-week-old wide edge are different trades'). It also outlines limits (60-day TTL, snapshot start date) but lacks explicit when-not-to-use or direct 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?

Description aligns with annotations (readOnlyHint, idempotentHint, etc.). It details behavioral traits: walks the ladder, returns fill metrics, warns about thin legs and forced directional risk. Adds context beyond annotations, such as the dominant loss mode from partial basket fills.

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 clear sections for each mode. It is appropriately detailed for a complex tool, with front-loaded purpose and no unnecessary words. 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?

Despite no output schema, the description thoroughly explains return values for both modes (e.g., top_of_book, vwap_fill_price, capture_ratio, thin_legs). Covers all parameters and behavioral nuances, making the tool self-contained for correct invocation.

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

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

With 100% schema coverage, the description adds significant meaning: explains mode selection via market vs event, default side behavior (auto for basket), interpretation of size_usd (spend vs target proceeds in single-market, settlement notional in basket). Provides nuanced usage guidance 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 the tool performs a 'realizable-vs-theoretical edge check against live CLOB order-book depth,' specifying two distinct modes (single-market and basket). It uses specific verbs and resource references, and the unique purpose distinguishes it from siblings like polymarket_arbitrage and polymarket_edges.

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 instructions: 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500.' It explains why (theoretical overround not capturable, partial fills create directional risk) and provides clear context for when to use versus 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?

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false. The description goes far beyond by detailing safety fields (compatibility_warning, temporal_alignment, skipped counters), explaining how spreads are computed (Kalshi − Polymarket), and noting that real spreads are rarer than the shortcut list suggests—providing rich behavioral context.

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 lengthy but well-organized with clear labels (TWO MODES, RESPONSE, SAFETY FIELDS) and front-loaded with the core purpose. Every sentence contributes useful information, though some details could be streamlined for an AI agent.

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

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

Despite lacking an output schema, the description thoroughly explains the response structure (leg-by-leg prices, spread arrays, safety fields) and addresses potential edge cases (mismatched bet shapes, temporal gaps). Given the tool's complexity and rich annotations, the description is complete and self-contained.

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

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

Schema description coverage is 100%, with each parameter documented. The description adds value by explaining the two modes, providing concrete examples of topic values, and specifying that explicit parameters override topic mappings—clarifying interaction semantics 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 that the tool computes cross-venue spreads between Kalshi and Polymarket, specifies two operation modes (pre-mapped topic shortcuts and explicit parameter pairings), and differentiates itself from sibling tools like polymarket_arbitrage by focusing on same-question spread across venues.

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 topic vs explicit modes, details how parameters interact, and warns that most pre-mapped topics are not tradeable due to compatibility issues. However, it does not explicitly contrast with alternatives like polymarket_arbitrage, relying on the distinct purpose.

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 readOnly and non-destructive. Description adds scoping context (by identifier), which is valuable 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?

Three sentences, no wasted words, front-loaded with purpose. Highly efficient.

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

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

For a simple tool with one optional parameter and no output schema, the description covers behavior, scoping, relationships, and usage context completely.

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%, baseline 3. Description reinforces the optional key behavior and adds context about listing all keys when omitted.

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 action (retrieve/list) and resource (saved values). Distinguishes 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?

Explicitly says when to use it (look up context stored earlier) and implies pairing with remember and forget. Could mention when not to use but 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?

The description discloses key behaviors beyond annotations, such as the mark_read parameter flagging events as read to affect subsequent calls. It aligns with annotations (readOnlyHint=true, destructiveHint=false, idempotentHint=true) 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 four sentences long, front-loaded with the core purpose, and every sentence adds useful information 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?

Despite no output schema, the description lists what is returned (source, citation_uri, raw event payload) and covers all parameters. It also mentions polling suitability and an alternative endpoint, making it complete for this 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?

The description adds meaning beyond the schema by providing examples (e.g., 'sec_8k') and explaining the effect of mark_read. Since schema coverage is 100%, baseline is 3, and the description adds value, earning 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 pulls fired events from the subscription feed and returns the most recent alerts with specific fields like source, citation_uri, and raw event payload. It is specific and distinct from sibling 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 mentions that polls work fine and provides an alternative endpoint (GET registry.pipeworx.io/alerts.json) for scripts and dashboards, giving context on when to use the tool. However, it does not explicitly state when not to use it or compare to siblings.

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

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint. The description adds critical behavioral details: fans out to multiple sources, fallback from GDELT to GNews, USPTO soft-fail, and output format. 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 front-loaded with example queries, then explains sources, parameters, and alternatives. It is longer than minimal but each sentence adds useful information. Could trim minor caveats like USPTO soft-fail date.

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 no output schema, the description explicitly states the return structure: 'changes[] grouped by source + total_changes count + pipeworx:// citation URIs'. It covers all key aspects: data sources, parameter formats, fallback behavior, and alternative tool usage, making it fully contextual.

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 covers 100% of parameters with descriptions. The description adds value by illustrating 'since' with relative shorthand examples ('7d', '30d') and clarifying 'value' accepts ticker or CIK. Minor room for improvement (e.g., 'type' only supports 'company' already in 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 provides a 'change feed for a company in the last N days/weeks/months' using multiple sources, and explicitly distinguishes from the sibling 'entity_profile' tool for static profiles.

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 guidance by listing example queries ('What's new with X', 'latest on Y') and directly advises using 'entity_profile instead when you want the static profile'. This helps the agent decide between 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?

Discloses important behavior beyond annotations: memory is key-value paired and scoped by user identifier. Also mentions persistence differences for authenticated vs. anonymous users. 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?

Four sentences with no wasted words. Key information is front-loaded: purpose and when to use. Efficient and structured.

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 simplicity (2 required params, no output schema), the description is complete. It covers purpose, usage, behavioral traits, and mentions companion tools. 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 already covers 100% of parameters with descriptions, so baseline is 3. The description adds contextual examples of what keys might be (e.g., 'subject_property', 'target_ticker'), which adds value beyond the schema, justifying a higher score.

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

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

The description clearly states the tool's purpose: 'Save data the agent will need to reuse later — across this conversation or across sessions.' It uses specific verbs and nouns (save data, key-value pair) and distinguishes from sibling tools like 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 states when to use: 'when you discover something worth carrying forward.' Also provides guidance on alternatives: 'Pair with recall to retrieve later, forget to delete.' This helps the agent decide when to use this tool versus siblings.

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

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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, and openWorldHint=true, so the safety profile is clear. The description adds minimal extra context (snapshots implies current state), but does not contradict 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 extremely short (two words), but it is under-specified. While concise, it omits critical information about usage and parameters, making it insufficient for an agent to correctly invoke the tool.

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

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

Despite having an output schema and rich annotations, the description lacks explanation of the parameter and the nature of the snapshot data (e.g., time range, granularity). This leaves the agent without enough context to use the tool 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?

The input schema has one parameter (station_id) with 0% description coverage. The description does not explain the parameter's meaning, format, or examples beyond what is in the schema examples. This fails to compensate for the lack of parameter 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 'Reservoir storage snapshots' clearly indicates the tool provides snapshot data about reservoir storage, with a specific resource (reservoirs) and implied action (get snapshots). It is not a tautology and differentiates from sibling tools by focusing on reservoir storage data.

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 when to use or not use, nor any context about 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 indicate readOnly, openWorld, idempotent, and non-destructive. The description adds value by revealing internal cascading through multiple endpoints, auto-disambiguation for company, and citation URIs in output. 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?

Description is a single paragraph, front-loaded with helpful examples and clear structure. Every sentence adds value, though it is somewhat verbose but not wasteful. Concise enough for an AI agent.

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

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

Given the 2 required parameters, rich annotations, and no output schema, the description covers return values, internal behavior, and citation URIs comprehensively. It lacks explicit error handling behavior, but overall it is complete for typical use.

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 enhances schema by giving example inputs, explaining return fields for each type, and noting auto-disambiguation. This adds meaningful context 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 resolves user-spoken names to canonical/official identifiers. It uses specific verbs like 'resolve' and specifies resources (ticker, CIK, RxCUI). It distinguishes from siblings by stating 'Use FIRST whenever you have a name but need an ID,' implying its primary role for ID 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?

Explicitly states 'Use FIRST whenever you have a name but need an ID,' providing clear when-to-use guidance. It also mentions it replaces 2-3 manual lookups, but lacks explicit when-not-to-use or alternative tool references.

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, idempotentHint, and no destructive hint, establishing a strong safety profile. The description adds value by detailing the probing mechanism, ranking logic, and output elements (score, confidence, signal density) without contradicting 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 extremely concise: two sentences. The first sentence states the core action and mechanism, the second provides a concrete use case and output summary. 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 mentions the ranked list with score, confidence, and signal density per entity, which is helpful. It also references the underlying tool ai_visibility_check. However, it could elaborate on the exact return format or define signal density for full completeness.

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 concise descriptions. The tool description enriches understanding by explaining that the first entity is treated as the 'subject' for narrative and that ranking uses ai_visibility_check. This adds context 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 compares AI visibility across multiple entities side-by-side, uses ai_visibility_check, ranks by score, and highlights most/least recognized. It distinguishes from sibling tools by specifying the competitive audit use case and mentioning reliance on ai_visibility_check.

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 it is useful for competitive AI-marketing audits and gives an example question. It implies usage for multiple entities (2-8), and contrasts with single-entity use via ai_visibility_check. However, it does not explicitly mention when not to use or compare to alternatives like compare_entities.

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 read-only, open-world, idempotent, non-destructive. Description extends this by detailing the external services called, the return format, and graceful partial failure handling including timing for bundlephobia.

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?

Single paragraph that efficiently covers purpose, usage, limitations, and behavior. Every sentence serves a purpose 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?

Despite no output schema, the description thoroughly explains the return value structure, including summary fields, advisory detail, links, and alternative versions. Also covers partial failure behavior completely.

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 clear descriptions for both parameters. The tool description adds no significant extra meaning beyond what the schema provides, so baseline 3 applies.

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

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

The description clearly states it is a composite check for npm packages, aggregating data from deps.dev and bundlephobia. It specifies the verb (scan), resource (npm package), and distinguishes from siblings by noting ecosystem limitations and alternative 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?

Explicitly states when to use: when an agent asks about safety, popularity, or size of an npm package. Also provides when-not-to-use guidance (non-NPM ecosystems) and mentions alternative direct use of deps.dev:version.

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, idempotentHint=true, etc. Description adds algorithmic details: BGE-base-en embeddings, cosine similarity, 500-char overlapping windows, 200K char cap with truncation flag. 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, concise and front-loaded: first sentence defines purpose, second adds usage guidance and technical details. 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?

No output schema, but description compensates by explaining return format (top-N passages with char offsets and similarity scores). Also covers technical constraints (200K char limit, truncation flag) and embedding details, making it complete.

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

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

Schema coverage is 100%, so baseline 3. Description adds context for 'text' (fetched record) and 'query' (natural-language), but schema already fully describes each parameter. Default limit mentioned, but no substantial additional semantics.

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

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

Clearly states 'Semantic search INSIDE a fetched record' with specific verb and resource. Distinguishes from sibling tools like ask_pipeworx_grounded by describing its role as a passage-level retriever with offsets and scores.

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 the record is too big to cram into the prompt' and pairs with ask_pipeworx_grounded, providing a clear when-to-use and complementary tool. Implies alternative for small records.

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, idempotentHint=true, and destructiveHint=false, indicating a safe read operation. However, the description adds no behavioral context beyond these annotations (e.g., response format, rate limits, or side effects). It fails to provide added 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?

While the description is very short (three words), it is under-specified rather than concise. It lacks necessary information for an agent to use the tool effectively, so it does not earn its place as minimal yet complete.

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 zero schema coverage and no parameter descriptions, and despite having an output schema, the description is completely inadequate. There is no explanation of what metadata is returned, how to interpret results, or when to invoke this 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?

The only parameter 'station_id' has no description in the schema (0% coverage), and the tool description does not explain valid values, format, or examples. The examples 'SHA' and 'ORO' are unannotated. The description adds no semantic meaning to the parameter.

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 'Station metadata.' is vague and does not specify what the tool retrieves about a station. It lacks a specific verb and resource, making it unclear whether it returns metadata, list of stations, or other details. It does not distinguish from any sibling tools.

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

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

No guidance is provided on when to use this tool versus alternatives. There is no mention of prerequisites, context, or exclusion criteria. The description offers no help in tool selection.

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: requires OAuth account, verifies phone for SMS (with 10/day cap), and webhook auto-disabled after 10 consecutive failures. Annotations (readOnlyHint=false, idempotentHint=true) align with the description's mention of idempotent behavior.

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 thorough but slightly verbose. It is well-structured with clear sections for types and delivery, but could be tightened without losing essential details. Every sentence adds value, but the length might deter some agents.

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 (3 params, nested objects, multiple subscription types, delivery options), the description covers all necessary context: required vs optional parameters, constraints, return value, and behavioral notes. No output schema exists, but the description adequately explains 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 coverage is 100%, but the description adds rich detail: explains each type with examples, parameter requirements (e.g., 'sponsor or condition required' for clinical_trial), and delivery constraints (phone verification, webhook secret). This goes well 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's purpose: 'Create a proactive monitoring subscription to a live-data event stream' and notes it returns the subscription ID. It distinguishes this tool from siblings like list_subscriptions, unsubscribe, and others by focusing on creation of subscriptions.

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 specifies the required account type (Pipeworx OAuth, not anonymous/BYO), lists supported subscription types with examples, and explains delivery channels. It provides guidance on when to use (proactive monitoring) but could more explicitly state when not to use or compare to 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?

Annotations already provide readOnlyHint, openWorldHint, idempotentHint, destructiveHint=false. The description adds that it returns category-bucketed example questions with tool+argument shape, but does not contradict annotations. Some extra context beyond annotations, but not extensive.

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 front-loaded with user queries and well-structured, but slightly verbose with enumerated categories. Still, every sentence adds value and it remains 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?

Without an output schema, the description sufficiently explains the return format (category-bucketed example questions). The tool is simple (0 required params, 1 optional), and all needed information is covered.

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 description in schema. The description adds meaning by listing example topic values ('finance', 'pharma', etc.) and explaining the effect of omission vs. passing the parameter, going beyond the schema's brief 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 explicitly states it is the onboarding entry point to show what Pipeworx can ask, returns category-bucketed example questions, and distinguishes itself from siblings like ask_pipeworx and discover_tools by being the first-use tool.

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

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

Provides explicit guidance: 'Use this FIRST when you do not yet know what Pipeworx can do' and mentions alternatives (meta-tools). Also explains when to omit vs. pass the topic argument.

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: it explains that the row is deactivated (not deleted) and that historical events stay available. This is consistent with annotations (destructiveHint=false, idempotentHint=true) and provides behavioral details that help the agent understand consequences.

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 unnecessary words. Front-loaded with the core action. Every sentence serves a purpose: action, ownership constraint, behavioral detail. Perfectly 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?

For a single-parameter tool with no output schema, the description covers purpose, ownership, deactivation behavior, and historical availability. No gaps remain 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% and the description adds value by explaining that only own subscriptions can be canceled (ownership enforcement), which gives meaning to the 'id' parameter beyond its type and schema 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 action ('Cancel a subscription by id'), specifies the resource (subscription), and differentiates from siblings like 'subscribe' and 'list_subscriptions' by noting deactivation vs deletion. The verb 'Cancel' is specific and appropriate.

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 (when you want to cancel a subscription) and notes ownership enforcement. It mentions that historical events remain via recent_alerts, hinting at alternatives for permanent deletion, but does not explicitly state when not to use or name an alternative tool for deletion.

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, idempotentHint, and destructiveHint=false, indicating a safe, idempotent read operation. The description adds behavioral details beyond annotations, such as return structure (verdict, extracted form, actual value with citation, percent delta) and the fact it replaces multiple 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 front-loaded with example queries and is informative, but slightly verbose. Every sentence adds value, though some redundancy could be trimmed. Overall concise enough for the information conveyed.

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 a single parameter and no output schema, the description fully explains what it returns (verdict, extracted form, actual value with citation, percent delta) and its domain limitations. It is complete for an AI agent to select 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?

Schema description coverage is 100%, so baseline is 3. The description adds meaning by providing natural-language examples and clarifying that the domain is company-financial claims for public US companies. This helps the agent understand the parameter's expected input and constraints 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 starts with natural-language query examples and clearly defines the tool as claim verification against authoritative sources, specifically for company-financial claims via SEC EDGAR + XBRL. It distinguishes itself by noting it replaces multiple sequential calls, making it clear what the tool does and how it differs from siblings.

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 'Use whenever the agent needs to check whether something a user said is factually correct' and specifies the current domain. It provides clear context but lacks explicit when-not-to-use instructions or alternatives, though the sibling list and context imply alternatives exist.

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