uluesky

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

Annotations already declare read-only, open-world, idempotent. Description adds cost model (free default, BYO key for Anthropic), and return format details (per-model {score, confidence, signals, raw_response}). Could mention rate limits but still adds 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?

Three sentences, front-loaded with purpose, no redundancy. Every sentence provides essential 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 4 params, no output schema, and annotations covering safety/idempotency, the description explains return format, model selection, and optional parameters thoroughly. Adequate for an AI agent to use correctly.

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

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

Schema coverage is 100%, and description adds context: _apiKey only needed for anthropic model, context for disambiguation. Examples given for entity and models. Adds meaning 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 uses a specific verb ('probe') and resource ('LLMs') and clearly states the outcome: score visibility (0-100) per model. It distinguishes from siblings like 'scan_competitor_ai_presence' by covering general brand/topic checks.

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

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

It explicitly states default model and when to add Anthropic, and lists use cases ('AI-marketing audits, pre-launch brand checks, competitive monitoring'). Does not say when NOT to use, but context is clear.

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 safety profile. Description adds that it returns structured answers with citation URIs. No contradictions.

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

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

Front-loaded with key directive. Structured with examples. Slightly long but 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?

Covers what tool does, when to use, what it returns. No output schema but description mentions return structure. Complete for a complex 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%, baseline 3. Description adds context that question is natural language, accepts multiple aliases, and provides examples, adding value beyond schema.

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

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

Clearly states it routes questions to a large set of tools for factual data. Distinguishes from siblings like ask_pipeworx_grounded and deep_research. Specific verb+resource.

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

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

Explicitly says 'PREFER OVER WEB SEARCH' and provides extensive examples of when to use. Clearly guides when to step up 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?

The description adds significant behavioral context beyond annotations: it explains the extra LLM call, the refusal reasons ('not_in_source', 'no_tool_match', etc.), the evidence extraction method, and the structured response format. 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 well-structured, starting with purpose, then behavior, then use cases and cost trade-off. It is moderately long but every sentence adds value; no fluff. Could be slightly more concise, but still effective.

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 details the return format (answer, evidence, confidence, source, fetched_at, refusal_reason) and failure modes. It distinguishes the tool from 36+ siblings and provides complete guidance for an agent to decide and use correctly.

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

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

The input schema has 100% description coverage, already documenting all param aliases and the natural language question. The description only reinforces that 'question' accepts aliases, adding no new semantic 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 as a 'hallucination-resistant answer mode for high-stakes reads,' explicitly contrasting with ask_pipeworx. It details the routing, data extraction process, and structured output, making the tool's function unambiguous.

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

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

The description provides explicit guidance on when to use ('whenever an answer will be quoted, cited, or acted on') and when not to ('prefer ask_pipeworx for casual lookups'), with specific examples like financial verdicts and medical lookups. It also notes the extra cost (one LLM call) vs the sibling tool.

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

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

Annotations already indicate read-only, idempotent, non-destructive behavior. The description adds extensive behavioral details: fan-out examples, response shapes, resolver contract, parent event extractor, news fields, safety mechanisms, and resolution-rule risk. 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 long but well-structured with sections (CLASSIFIERS, FAN-OUT EXAMPLES, etc.) and front-loaded with core purpose. Every sentence adds necessary detail; slight length reduction possible but justified by 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 complexity (multiple parameters, no output schema, many behavioral nuances), the description is highly complete, covering resolution matching, parent events, news fallback, cancellation rules, and more. 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%, and the description adds further context for all three parameters, including input formats for market, depth options, and include_raw explanation. Adds significant value beyond the schema.

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

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

The description clearly states it researches a Polymarket bet by pulling Pipeworx data, specifying multiple input types (slug, URL, question text). It distinguishes from siblings like ask_pipeworx and polymarket_arbitrage by focusing on bet research with evidence packet and market comparison.

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

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

Explicitly says 'Use for "should I bet on X", "what does the data say about Y", or "is there edge in Z"' and provides scenarios and examples. Lacks explicit exclusion of when not to use, but otherwise clear.

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?

Beyond annotations, the description details data sources (SEC EDGAR/XBRL for companies, FAERS for drugs), specific financial metrics (revenue, net income, cash, debt) and handling of off-calendar fiscal years. It also explains result sorting 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 trigger phrases and is information-dense. Some repetition of the preference guidance could be trimmed, but overall 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?

Given no output schema, the description covers return format (paired data, citation URIs, sorted by primary metric) and data sources for both types. It fully addresses the complexity of the tool without missing critical details.

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 description adds extra context: explains 'company' values are tickers/CIKs, 'drug' values are names, notes off-calendar handling. This exceeds bare schema descriptions, though the schema already has good descriptions.

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

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

The description clearly states the tool's purpose: side-by-side comparison of 2-5 companies or drugs in a single parallel call. It uses specific verbs like 'compare', 'rank', and provides example queries. It distinguishes from sibling tools like entity_profile by emphasizing it avoids sequential lookups.

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 to 'ALWAYS PREFER over sequential single-pack lookups when comparing entities.' Provides concrete trigger phrases and explains that it replaces 8-15 lookups, giving clear guidance on when to use this tool vs 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?

Adds context beyond annotations: account needed, paid plan for thorough depth, returns gaps[], not open-web search, 15-60s latency. Contradicts no 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?

Well-structured with key info front-loaded, but slightly verbose. Each sentence adds value, but could be trimmed without losing clarity.

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?

Thorough for a complex tool: explains multi-source, parallel decomposition, return format (findings with citations and gaps), and limitations. No output schema, but description adequately covers return values.

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%; description adds meaning: question is natural language, depth controls number of facets (quick=3, standard=5, thorough=8). Enhances enum understanding.

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 Pipeworx's 1259 STRUCTURED data sources' and distinguishes from siblings like ask_pipeworx and ask_pipeworx_grounded.

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 when to use: 'Best for broad/multi-part questions over structured data.' Provides alternatives for single lookups (ask_pipeworx) and breaking news (ask_pipeworx). Also notes account requirements.

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 discloses return format (top-N tools with names, descriptions, and full input schemas) and that results are ready to call directly. Annotations confirm read-only, idempotent, non-destructive behavior, which the description supports.

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?

Five sentences with no fluff: opens with purpose, lists domain examples, explains return value, and gives usage hint. Information is front-loaded and each 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?

Given no output schema, the description adequately explains what is returned and when to use it. Could mention error handling or limits, but overall sufficiently complete for discovery and subsequent tool invocation.

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

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

Schema coverage is 100%, so baseline is 3. Description adds value by explaining that query has aliases (task, q, description, search) and giving examples, which clarifies parameter usage beyond the schema.

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

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

The description clearly states the tool finds tools by describing data or task, lists specific domains (SEC filings, FDA drugs, etc.), and distinguishes itself as a high-level discovery tool from sibling tools that are specific actions.

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

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

Explicitly advises calling this FIRST when many tools are available and you want to see options. Provides example tasks and domains. Lacks explicit 'when not to use' statements but otherwise strong guidance.

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

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

The description goes well beyond annotations (readOnlyHint, openWorldHint, idempotentHint) by detailing the internal behavior: fans out across SEC EDGAR, XBRL, USPTO, news, GLEIF; returns specific fields with sorting and fallbacks; and notes a soft-fail for patents. This adds rich context about data sources, accuracy, and idempotency 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 a single dense paragraph, but every sentence adds value: examples, usage preference, data source enumeration, return field details, and limitations. It could benefit from bullet points for scanning, but it is front-loaded with examples and efficient in conveying a lot of information without waste.

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, the description is remarkably complete: it covers input format (ticker/CIK, no names), output fields (cik, company_name, filings, fundamentals, patents with caveat, news fallback, LEI), and limitations (patents sunset, name requirement). No output schema exists, so the description carries full burden and succeeds comprehensively.

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 already describes both parameters (type enum and value string) with 100% coverage. The description adds valuable nuance: it reiterates that only 'company' type is supported, clarifies that value accepts ticker or zero-padded CIK but not names, and directs to resolve_entity for names. This extra guidance elevates it above baseline 3.

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

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

The description starts with concrete examples like 'Tell me about X' and 'company profile for Microsoft', then explicitly states 'full cross-source profile of a US public company in ONE parallel call.' This clearly identifies the verb (profile), resource (US public company), and scope (cross-source, parallel), distinguishing it from single-source or chaining tools.

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

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

The description provides explicit when-to-use guidance: 'ALWAYS PREFER over chaining single-pack SEC/XBRL/news lookups when the user asks for a holistic view.' It also specifies when not to use it: 'names not supported (use resolve_entity first if you only have a name).' This covers both preferences and 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 indicate destructiveHint=true and idempotentHint=true. The description adds value by explaining the destructive action ('Delete') and providing context ('clear sensitive data'), 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?

Two concise sentences: the first states the action, the second provides usage guidance. No wasted words.

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

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

For a single-parameter delete tool with full schema coverage and clear annotations, the description provides sufficient usage context and pairs with sibling tools. 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?

With 100% schema description coverage, the description does not add additional meaning beyond the schema's 'Memory key to delete'. 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 uses a specific verb ('Delete') and resource ('a previously stored memory by key'), and distinguishes itself from sibling tools like 'remember' and 'recall'.

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

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

The description explicitly states when to use the tool ('context is stale, task done, clear sensitive data') and suggests pairing with related tools ('remember and recall').

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false. The description adds value by detailing the process (fetches page, extracts title/description/key links, emits standard format) and output format (single text blob). 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 concise: two sentences covering purpose and process, followed by a bullet list of use cases. No redundant information, and the main action is front-loaded.

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

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

With only 2 parameters and no output schema, the description fully explains the tool's behavior, output format, and use cases. It is complete enough for an agent to understand and invoke correctly.

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

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

Schema coverage is 100% for both parameters (url and max_links). The description doesn't add significant detail beyond the schema, as it only mentions the output format. Baseline 3 is appropriate since schema already describes parameters adequately.

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 generates an llms.txt file for a URL to help AI crawlers index the site. It specifies the verb 'Generate', the resource 'llms.txt file', and the purpose 'index the site cleanly'. This distinguishes it from siblings like ai_visibility_check and scan_competitor_ai_presence.

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 lists explicit use cases: getting a client's site indexed, drafting for own project, or auditing competitor. This provides clear context for when to use, though it doesn't explicitly state when not to use or mention 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 readOnly, openWorld, idempotent, and non-destructive hints. The description adds context about return content (posts, authors, timestamps, engagement counts), which goes beyond annotations by specifying what the output looks like. 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?

Two sentences, front-loaded with the core action. Every word serves a purpose: verb, resource, examples, return list. No redundancy or filler.

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

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

Given the tool's simplicity (2 optional parameters, read-only, idempotent) and the presence of an output schema (not shown but referenced), the description fully covers what the tool does and what it returns. No missing information needed for an agent to decide to use it.

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

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

Schema coverage is 100% with descriptions for both parameters. The description adds value by providing example feed URIs (e.g., 'discover', 'what's-hot'), which clarifies the expected format and common values for feed_uri. The limit parameter is adequately described in the schema.

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

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

The description clearly states the tool retrieves posts from a Bluesky feed, with examples like 'discover' and 'what's-hot'. It mentions return content (authors, timestamps, engagement counts), and distinguishes from sibling tools like 'get_posts' by focusing on feed-level retrieval.

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 a clear use case (getting feed posts) but does not explicitly state when to use this tool versus alternatives (e.g., search_posts, get_posts). It implies usage for feed exploration but lacks exclusions or alternative recommendations.

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 cover read-only and idempotent behavior. The description adds what data is returned but no additional behavioral traits like rate limits or pagination.

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

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

Two sentences, no fluff, front-loaded with action and result. Every word earns its place.

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

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

Given the simple tool, output schema present, and clear description, it is fairly complete. Could mention if result is paginated or sorted, but not critical.

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 reinforces that the handle is used but adds no extra 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 retrieves followers by handle and lists returned fields. It is specific but does not distinguish from sibling tools like 'get_follows' or 'get_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 implies usage context (get followers of a user) but provides no guidance on when not to use it or alternatives among siblings.

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

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

Annotations already mark the tool as read-only, open-world, idempotent, and non-destructive. The description adds return value details but does not cover potential behavioral traits like pagination or authentication requirements.

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 single sentence. No wasted words, but lacks structured breakdown of context or usage.

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 comprehensive annotations, the description adequately summarizes return fields. However, it omits optional details like pagination or limit behavior.

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

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

Input schema has 100% description coverage for both parameters. The description adds no further meaning beyond what the schema provides, so 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 action (get), the resource (accounts a user follows), and the returned fields (handles, display names, etc.). It effectively distinguishes itself from siblings like get_followers.

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 explicit guidance on when to use this tool versus alternatives. The name and description imply usage for fetching follows, but no contrast with siblings or exclusion criteria is 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 cover safety (readOnlyHint, destructiveHint) and idempotency. The description adds behavioral context about returned fields including threaded replies, but doesn't discuss pagination or rate limits.

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

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

Two sentences, no filler. Purpose first, then return fields. Efficient and front-loaded.

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

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

With output schema present and full parameter coverage, the description adequately covers purpose and return data. Slightly lacks mention of list structure or pagination, 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?

Schema coverage is 100%, so baseline is 3. The description adds no additional meaning about parameters (limit, handle) 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 verb 'Fetch', the resource 'posts from a Bluesky user's timeline', and lists specific returned fields (text, timestamps, likes, etc.). This distinguishes it from siblings like get_feed or get_thread.

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., get_feed, search_posts). Missing explicit 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?

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds the return data list and input format, but does not disclose additional behavioral traits like authentication needs or error handling beyond what annotations provide.

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

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

Two sentences: first states purpose and input, second lists returns. No wasted words, and critical information is front-loaded. Every sentence earns its place.

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

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

Given the simple single-parameter input, rich annotations, and the presence of an output schema (which we infer covers the return fields), the description provides a complete overview. It lists all key return fields and specifies the handle format, leaving no major gaps for a lookup tool.

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

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

Schema coverage is 100% with a clear description for the handle parameter. The description repeats the format example but adds no new meaning beyond the schema, resulting in a baseline score of 3.

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

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

The description clearly states the tool looks up a Bluesky user's profile by handle, specifying the resource (profile) and action (look up). It lists specific return fields (display name, bio, follower/following counts, avatar, verification status), distinguishing it from siblings like resolve_handle.

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 for when to use (when you need a profile by handle) but does not explicitly exclude alternatives or differentiate from similar siblings like entity_profile or resolve_handle. The usage is implied but lacks direct comparison.

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

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

Annotations already declare readOnlyHint=true and destructiveHint=false, providing safety context. The description adds behavioral details such as returning conversation order and engagement data, which enriches understanding 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?

A single sentence that efficiently conveys the action and return, with no wasted words. Front-loaded with the verb and resource.

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 annotations covering idempotency and safety, the description is complete. It mentions key return elements and the ordering, leaving no major gaps for this 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 the description does not add beyond what the schema already provides for the single parameter 'post_uri'. Thus, baseline score of 3 is appropriate.

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

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

The description clearly states the tool fetches a post thread by URI, specifying the return includes parent post and all replies in conversation order with timestamps, authors, and engagement data. This distinguishes it from siblings like get_posts or get_feed.

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?

While no explicit when-to-use or alternatives are given, the description's specificity for thread retrieval implies its use case. For a simple fetch tool, this is sufficient, but lacks explicit guidance on 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 already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so description's mention of 'active subscriptions' and return fields adds moderate value. No contradiction, but description doesn't disclose additional behavioral traits beyond annotations.

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

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

Two sentences with zero waste: first defines purpose and output, second provides usage guidance. 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, description lists all return fields. However, lacks mention of pagination or ordering, which would be helpful for a list tool. Still sufficient 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% with a single boolean parameter fully described. The description does not reiterate parameter details, which is acceptable per guidelines. 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 the verb 'list', resource 'subscriptions', and scope 'caller's active'. It lists specific return fields (id, type, params, created_at, last_fired_at, fire_count), making it highly specific and distinguishable from siblings like subscribe and unsubscribe.

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 when to use: 'before adding more subscriptions' or 'to find an id to cancel'. This provides clear context, though no explicit alternative or when-not-to-use is mentioned. Given sibling tools like subscribe, it's adequate.

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?

Exceeds annotations by disclosing rate limits (5 per identifier per day), free pricing, and no quota impact. Also notes team digests and roadmap influence. 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?

Concise at 5 sentences with no redundancy. Front-loaded with purpose, then expands on usage, constraints, and tips. 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?

Given 3 params (2 required, one nested object) and no output schema, the description covers all necessary context: purpose, usage scenarios, formatting advice, rate limits, and quota exemption. Lacks return value description, but that is minor for a feedback 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 description need not add param details. But it adds valuable behavioral context (e.g., 'describe issue in terms of tools/packs'). Extra guidance raises it above baseline 3.

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

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

The description clearly states the tool's purpose: sending feedback to Pipeworx about bugs, features, or praise. It uses specific verbs ('tell', 'describe') and identifies the resource (Pipeworx team). It implicitly distinguishes from sibling tools as the only feedback mechanism.

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 examples (bug, feature/data_gap, praise) and what to avoid (pasting end-user prompt). Although no alternatives are mentioned due to uniqueness, the guidance is comprehensive.

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, destructiveHint. Description adds caching behavior (5min-1h), no PII, source (CF analytics), enhancing transparency.

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

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

Two sentences plus bullet points; every sentence adds unique value. No redundancy or filler.

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

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

Given one parameter, no output schema, and rich annotations, the description fully covers purpose, usage, and behavioral traits. Agent has all needed info.

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 (window) with enum and description. Description adds context: short windows surface hot trends, longer show steady-state demand, 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?

Description clearly states verb 'returns' and resource 'top tools, top packs, and total call volume on Pipeworx'. Differentiates from siblings by highlighting unique use cases like discovering hot data sources and confirming canonical 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 lists three use cases (e.g., discovering hot data, confirming canonical tool) that guide when to use. No explicit when-not, but context is clear enough.

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

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

Annotations declare readOnlyHint, idempotentHint, and non-destructive. The description adds extensive behavioral details: monotonicity violation checks, partition_sum checks, Jaccard similarity threshold (0.30), placeholder filtering, fill_check via polymarket_fill_risk. 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 detailed but well-structured with clear sections (SEMANTIC ANCHOR, PARTITION FILTER, FILL CHECK). It is slightly long but each sentence adds useful information. Could be slightly more concise by splitting into bullet points.

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 thoroughly explains return values (opportunities[], partition_check) and behavioral details (fill_check, placeholder filtering). It also mentions custom sizing via a sibling tool. The description covers all necessary context for an agent to use the tool correctly.

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

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

Schema coverage is 100% with descriptions for event and topic. The description adds value by explaining what slugs look like (e.g., 'fed-decision-may-2026'), that full URLs work, and how topic functions as a seed question. This enriches the schema definitions.

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

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

The description clearly states the tool finds arbitrage opportunities on Polymarket via monotonicity violations and partition-sum checks. It specifies three modes: trending_scan (no args), event (specific market), and topic (cross-event). This distinguishes it from sibling tools like polymarket_edges or polymarket_edge_tracker.

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: call with no args for trending_scan, use event for a specific market, use topic for cross-event scanning. It explains when each mode is recommended. However, it does not explicitly state when not to use this tool or contrast with alternatives.

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

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

The description adds extensive behavioral context beyond the annotations (readOnlyHint, openWorldHint, etc.). It details caching (1h KV), response structure (by_segment, diagnostics), algorithmic details for each model family, and a 24h move warning. 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 verbose, especially with algorithmic details for each model family. It is front-loaded with the core purpose and use case. For a tool with three models and many knobs, the length is justified, but could be slightly more compact.

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 9 parameters, no output schema, and complex behavior, the description is remarkably complete. It explains caching, response structure, why segments can be empty, and knob effects. The only minor omission is a simple example, but overall it is thorough.

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 each parameter having a description. The tool description adds extra contextual guidance for parameters (e.g., 'min_kelly' skips too-small opportunities, 'max_spread_pp' tight-book threshold) and explains Polymarket fee structure. This adds value beyond the schema alone.

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

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

The description clearly states the tool scans Polymarket markets for opportunities where Pipeworx data disagrees with market price, with a specific use case ("what should I bet on today"). It distinguishes itself from siblings like polymarket_arbitrage and polymarket_kalshi_spread by focusing on Pipeworx-driven 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 explicit context on when to use the tool (discovering opportunities without paging hundreds of markets) and details the three response segments. It mentions Fed bets are excluded and explains diagnostic output for empty segments. However, it does not explicitly contrast with sibling tools or state when not to use it.

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

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

Provides comprehensive behavioral context: reads snapshots, returns time-series, expired opportunities, limitations on history depth and decay computation. Complements 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?

Long but every sentence adds value. Well-structured with paragraphs and clear sections. Slightly verbose but justified by 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?

Provides extensive detail on response fields (tracked, expired, snapshot_dates) and caveats (60-day TTL, decay from daily closes). Fully compensates for lack of output schema.

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

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

Schema covers 100% of parameters. Description adds defaults and constraints for 'days' and 'window', and explains the response structure in detail, compensating for missing output 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?

Explicitly states it provides edge persistence and decay telemetry from daily snapshots, answering a specific question about edge age and shrinkage. Distinguishes 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?

Clearly describes the use case and gives an example (fresh vs. old wide edge) and states limits (60-day TTL). Lacks explicit when-not-to-use or alternatives, but context is strong.

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, openWorldHint=true, idempotentHint=true, destructiveHint=false. Description adds rich behavioral detail: walks the ladder, returns fill metrics, and warns about forced directional risk in basket mode. No contradiction with annotations; description significantly augments them with operational specifics.

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 dense but well-organized with clear sections for single-market, basket mode, and usage guidance. Front-loaded with core purpose. Every sentence adds value, though could be slightly more concise. No fluff.

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 complexity (two modes, multiple return fields, no output schema), description is comprehensive. Lists all key return fields, explains behavior in each mode, and warns about risks like thin legs and directional exposure. No gaps in context for an AI agent to decide and invoke 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 has 100% description coverage, but tool description adds value by explaining required condition (one of market or event), default behavior for side in each mode, and interpretation of size_usd for single vs basket. Also notes clamp range (10–1,000,000). Enhances understanding beyond schema alone.

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 defines the tool as a realizable-vs-theoretical edge check against live order-book depth. Distinguishes two modes (single-market and basket) and lists specific output fields (top_of_book, vwap_fill_price, slippage_pp, etc.). Differentiated from sibling tools like polymarket_arbitrage and polymarket_edges by its focus on fill risk assessment.

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 using this tool before acting on polymarket_arbitrage SELL/BUY-EVERY-LEG signals or polymarket_edges trades above ~$500. Explains why: theoretical overround on thin books is not capturable, and partial basket fills convert arbitrage into unhedged directional positions. Provides strong context for when to invoke.

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 safe read-only behavior. Description adds substantial behavioral context: explains compatibility_warning conditions, temporal_alignment implications, and skipped counters. 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?

Well-structured with sections (TWO MODES, RESPONSE, SAFETY FIELDS) but verbose. Could be trimmed slightly, but the detail is justified given 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?

Despite no output schema, the description fully details response fields (prices, spread, compatibility_warning, temporal_alignment, skipped counters). Complete for an AI agent to use correctly.

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

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

Schema coverage is 100% with detailed descriptions for each parameter. Description further explains the two modes and how parameters interact (e.g., overrides). Adds significant meaning 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 computes cross-venue spread between Kalshi and Polymarket for the same resolving question. It uses specific verb+resource (compute cross-venue spread) and distinguishes from siblings like 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?

Explicitly describes two modes (topic vs explicit), warns that most pre-mapped topics return compatibility_warning, and explains when spreads are not meaningful (non-equivalent bet shapes, temporal misalignment). Provides guidance on interpreting success and failure.

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. The description adds useful context: scoping to identifier, pairing with remember/forget, and the retrieval/list dual behavior. 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?

Two sentences, no redundant information. Front-loaded with the core action, then provides use case and pairing. Every word serves a purpose.

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

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

Given the simplicity of the tool (one optional parameter, no output schema), the description covers behavior, scope, and relationship with siblings completely. No gaps identified.

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 parameter 'key' is already documented. The description reinforces the behavior (omit to list all keys) but doesn't add significant new meaning 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 action ('retrieve' or 'list') and the resource (values/keys saved via remember). It explicitly distinguishes from siblings by naming '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?

Provides clear use case ('look up context stored earlier... without re-deriving it from scratch') and explains behavior when key is omitted. Does not explicitly state when not to use or alternatives, but the pairing with remember/forget gives adequate guidance.

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

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

Description states mark_read:true changes state (flags events read), contradicting annotations readOnlyHint:true and idempotentHint:true. Per instructions, contradiction yields score 1.

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, front-loaded with main action, each sentence adds information. No fluff.

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?

Explains return value structure and side-effect of mark_read. Lacks mention of pagination or limit behavior, but sufficient for a simple read 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%; description adds value by explaining mark_read effect and tying parameters to returned data (e.g., source, citation_uri).

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 'Pull fired events from your subscription feed' and specifies key fields returned (source, citation_uri, raw payload) and filtering options (type, since, mark_read). Distinct from siblings like get_feed.

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 context for when to use (filtering, polling) and mentions alternative access via URL. Lacks explicit exclusions or comparison to sibling tools.

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

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

The description discloses key behaviors: fans out to multiple sources (SEC, GDELT/GNews, USPTO), includes fallback logic, notes API sunset, and explains output structure. This adds significant context beyond annotations which already indicate 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 comprehensive and well-structured, starting with example queries. While slightly long, every sentence adds value and no information is redundant. It could be trimmed slightly but is still effective.

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

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

Given no output schema, the description explains the return format (changes grouped by source, total_changes count, citation URIs). It covers all necessary aspects for the tool's 3 required parameters and provides complete contextual information.

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

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

Although schema covers all parameters with descriptions, the tool description adds additional meaning: explains 'since' format in detail, clarifies 'value' can be ticker or CIK, notes that 'type' only supports 'company', and provides usage tips. This exceeds the schema alone.

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: providing a change feed for a company over a time window, with specific example queries. It also distinguishes itself from the sibling tool entity_profile by specifying when to use that alternative.

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

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

The description explicitly provides usage guidance, including when to use this tool (e.g., 'What's new with X') and when to use entity_profile instead. It also recommends typical 'since' values like '30d' or '1m' for monitoring.

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 behavioral traits beyond annotations: key-value scoping by identifier, persistence differences for authenticated vs anonymous sessions. Annotations indicate idempotentHint=true and destructiveHint=false; description adds 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 a single paragraph that efficiently conveys purpose, usage, and behavioral details. It is front-loaded with the action and context, and every sentence adds value. Slightly verbose but justified.

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 two parameters, no output schema, and the existing annotations, the description fully covers when and how to use the tool, scoping, persistence, and relationships with sibling tools. Nothing essential is missing.

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

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

Schema coverage is 100% with descriptions for key and value. Description adds real-world examples and clarifies value as 'any text' with examples (findings, addresses, preferences), adding semantic value beyond the schema.

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

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

The description clearly states the tool's purpose: 'Save data the agent will need to reuse later' with specific examples (resolved ticker, target address, etc.). It effectively distinguishes from sibling tools like recall and forget by specifying the action and context.

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

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

Explicitly tells when to use the tool: 'Use when you discover something worth carrying forward.' It provides examples and differentiates between authenticated persistent memory and anonymous 24-hour retention, plus pairs with recall and forget for complete workflow.

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

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

The description adds value beyond annotations by revealing internal cascading behavior through multiple lookup endpoints and detailing return values (e.g., citation URIs). Annotations declare readOnlyHint and idempotentHint, and the description is consistent.

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 examples and uses a clear structure. Every sentence adds value, and it is as concise as possible given the detail needed for two entity types.

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 no output schema, the description fully compensates by describing return values for both types, including formats and citation URIs. It provides complete context for a tool with 2 parameters.

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 significantly enhances meaning by explaining input acceptance (e.g., 'ticker, CIK, or name') and output specifics (e.g., 'returns ticker + 10-digit CIK + company_name + citation URI').

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 names to canonical identifiers with specific examples (ticker, CIK, RxCUI) and supported entity types. It implicitly distinguishes from sibling tools like 'resolve_handle' by focusing on entities other than user handles.

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

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

Explicit guidance: 'Use FIRST whenever you have a name but need an ID.' It also describes when to use for each supported type and mentions the tool replaces multiple manual lookups.

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 that it returns a DID, which is consistent. However, it does not provide additional behavioral context beyond what the annotations and schema suggest.

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

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

The description is a single, concise sentence that conveys the core functionality without any extraneous information. Every word earns its place.

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

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

Given the tool's simplicity, an output schema is present, and annotations cover behavioral traits. The description adequately completes the picture for a straightforward conversion 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 input schema describes the single 'handle' parameter with full coverage. The description adds no new semantic meaning beyond what the schema already provides, so baseline score applies.

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

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

The description clearly states the tool's purpose: converting a Bluesky handle to a DID. It uses a specific verb ('convert') and resource ('Bluesky handle to DID'), and the tool is distinct from siblings like 'resolve_entity' due to its explicit focus on handle resolution.

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 use for programmatic account lookups but does not specify when not to use it or how it differs from similar siblings such as 'resolve_entity'. No explicit guidance on context or exclusions.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false. The description adds behavioral detail: it probes each entity with ai_visibility_check, ranks by score, and returns a ranked list with score, confidence, and signal density. This provides useful context beyond annotations without contradicting them.

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

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

The description is four sentences, front-loaded with the core purpose, followed by mechanism, use case, and return format. Every sentence serves a distinct purpose with no redundancy.

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

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

Given 4 parameters (1 required), no output schema, and 100% schema coverage, the description covers the operational logic well. It mentions entity limits (2-8), optional models and API key, and the returned fields. Minor omission: no mention of error conditions or rate limits, but read-only tool with annotations makes this acceptable.

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 value by explaining that the first entity is treated as the 'subject' for narrative and that the context parameter disambiguates common names. This semantic detail is not in the schema.

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

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

The description uses 'Compare' with a specific resource 'AI visibility across multiple entities side-by-side'. It distinguishes itself from sibling tool 'ai_visibility_check' (single entity probe) by clearly stating it probes multiple entities and ranks them. The verb and resource are precise.

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

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

The description explicitly provides a use case: 'Useful for competitive AI-marketing audits: does Claude know about us as well as our competitors?' This gives clear context. However, it lacks an explicit when-not-to-use or direct reference to the single-entity alternative (ai_visibility_check).

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?

Beyond annotations (readOnly, idempotent, openWorld), description reveals behavioral traits: partial failures degrade gracefully, bundlephobia's first measurement can take 5-30s, sources_failed will list timeouts. 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?

Somewhat lengthy (5-6 sentences) but well-structured: front-loaded with purpose and usage, then details. Minor redundancy (e.g., 'NPM ecosystem only in v1' and later again). Still earns its place.

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

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

Given no output schema, description fully details return format (summary fields, advisory details, links, alternative versions) and handles edge cases (partial failures, timeouts, sources_failed). Very 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 covers both parameters with descriptions (100% coverage). Description adds value by noting scoped packages (e.g., '@types/node') are accepted and that version defaults to latest, which is helpful but not essential beyond schema.

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

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

The description clearly states it's a composite 'should I add this npm package' check, specifying the resources (deps.dev, bundlephobia) and return summary. It distinguishes from siblings by focusing on NPM dependency analysis, which no other sibling tool does.

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

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

Explicitly tells when to use: when an agent asks about safety, popularity, size, or cost. It also notes NPM-only and gives guidance on other ecosystems ('PyPI / Maven / Cargo / Go fall under deps.dev:version directly').

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, covering safety. The description adds authentication requirement, which is a deployment detail rather than tool behavior. 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?

Two sentences with relevant information, but there is a missing space after the period in 'content.Requires'. This minor formatting issue prevents a higher score.

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

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

Given the simple parameter set (2 params, fully described schema), output schema, and annotations, the description provides adequate context. The authentication mention is useful but slightly ambiguous regarding tool 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?

Input schema has 100% coverage for both parameters, with descriptions for query and limit. The description does not add further semantic detail beyond what the schema provides.

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

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

The description clearly states it searches Bluesky posts by keyword, and lists return fields (author handles, timestamps, etc.). It is distinct from sibling tools like get_posts or get_feed, which serve different purposes.

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

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

The description indicates this tool is for searching posts by keyword, implying when to use it. It also notes the authentication requirement. However, it does not explicitly mention when not to use it or provide alternative tools.

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

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

Annotations already indicate a safe, read-only, idempotent tool. The description adds valuable behavioral details: embedding model (BGE-base-en), windowing (500-char overlapping), character cap (200K with truncation flag), and output information (passages with offsets). 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?

Single dense paragraph, front-loaded with purpose, then usage, then technical details. Every sentence provides value; no wasted words. Appropriate length 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?

Despite lacking an output schema, the description thoroughly explains what the tool returns (top-N passages with offsets and scores). Covers technical constraints (embeddings, windows, cap) and flags truncation. Mentions sibling tool integration, making it complete for an AI agent's 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% with descriptions for all parameters. The description enhances this by providing examples for 'query', explaining the nature of 'text' (document text), and clarifying the 'limit' default. Adds meaningful context beyond schema.

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

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

The description clearly states it performs semantic search inside a fetched record, with specific verb ('search') and resource ('inside a fetched record'). It provides concrete examples and distinguishes its use case from alternatives (e.g., when record is too big for prompt).

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 the record is too big to cram into the prompt'. Also suggests pairing with ask_pipeworx_grounded for a complementary workflow. Clear context on appropriate use.

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

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

The description goes beyond annotations by detailing delivery channel constraints (SMS cap, webhook auto-disable), verification requirements, and that feed is always on. No contradiction with annotations exists.

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

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

The description is front-loaded with the primary action and return value, and each subsequent section is informative. Slightly verbose but 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?

All three parameters are fully explained, and the tool's complex behavior (webhook signing, phone verification, persistence requirements) is covered. No output schema exists but return value is stated.

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 enriches the schema with concrete examples for each type and delivery option, such as item codes for sec_8k and topic for polymarket_edge. Schema coverage is 100% and the description adds significant narrative 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 creates a proactive monitoring subscription and returns the new subscription ID. It distinguishes from sibling tools like list_subscriptions and unsubscribe by focusing on creation.

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 prerequisites (requires Pipeworx OAuth account) and examples for each subscription type, but does not explicitly contrast with alternative tools or when not to use it.

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

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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true. The description adds that it returns 'category-bucketed example questions' with exact tool+argument shape, and explains behavior with and without the optional topic parameter.

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 detailed and front-loaded with keywords and examples. While somewhat long, each sentence adds value and the structure (purpose, examples, usage guidance) is clear.

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

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

Given the tool's role as an onboarding entry point, the description covers purpose, parameters, suggested use, and output nature. No output schema is needed as the description 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% and describes the topic parameter. The description adds value by explaining what values like 'finance' or 'pharma' mean, and clarifies behavior when omitted. Goes beyond schema's terse description.

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

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

The description clearly states the tool's purpose: to return example questions for a Pipeworx agent, organized by category, to help users understand what they can ask. It distinguishes itself from siblings (e.g., ask_pipeworx, discover_tools) by being the onboarding entry point.

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

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

The description explicitly says when to use: 'Use this FIRST when you do not yet know what Pipeworx can do for you, or to learn how to call the meta-tools.' It also explains optional topic filtering. Lacks explicit when-not-to-use statements, but provides clear context.

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

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

The description adds valuable behavioral details beyond annotations: ownership enforcement (only cancel own subscriptions), deactivation versus deletion, and availability of historical events via 'recent_alerts'. This complements the annotations well.

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 three sentences long, each sentence earning its place. It is front-loaded with the primary action and efficiently conveys constraints and effects 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 tool's simplicity (1 param, no output schema, good annotations, clear sibling tools), the description is complete. It covers purpose, ownership constraint, and data lifecycle, leaving no critical gaps.

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

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

Schema description coverage is 100% for the single parameter 'id', describing it as 'Subscription id (uuid) returned by subscribe.'. The tool description does not add additional parameter details beyond what is already in the schema, so the baseline score 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 'cancel' and the resource 'subscription by id'. It distinguishes itself from sibling tools like 'subscribe' and 'list_subscriptions' by specifying ownership enforcement and the effect of deactivation.

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

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

The description implies usage when the user wants to cancel their own subscription. It mentions ownership enforcement, which is a key usage constraint. However, it does not explicitly state when not to use or provide direct comparison to alternatives like 'list_subscriptions' or 'subscribe'.

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. Description adds that it uses SEC EDGAR + XBRL, returns specific verdicts, and replaces multiple calls, providing additional behavioral context 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?

Description is moderately concise, with each sentence adding value. It front-loads purpose and examples, but could be slightly trimmed without losing meaning.

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

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

Despite no output schema, description adequately explains return values and scope. It covers the tool's function and efficiency, though could mention error handling or limitations.

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

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

Schema coverage is 100% with a good description of the 'claim' parameter. Description reiterates the nature of claims (company-financial) but adds little beyond what is already in the schema.

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

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

Description clearly states it verifies natural-language claims against authoritative sources, using specific verbs like 'confirm or refute'. It distinguishes from siblings by focusing on claim verification with a specific scope (company-financial).

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 whenever the agent needs to check whether something a user said is factually correct'. Provides context but does not explicitly state when not to use or mention alternatives, though sibling tools exist.

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