uluesky

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

Annotations already provide safety traits (readOnly, idempotent, etc.), but the description adds value by detailing cost implications (free default vs. BYO key for Anthropic) and output structure (per-model scores, confidence). 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 three sentences long, front-loaded with the main purpose, and every clause serves a clear function. No redundant or filler content.

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 lack of an output schema, the description communicates the return format (per-model score, confidence, signals, raw_response + combined view) sufficiently. Could have mentioned pagination or rate limits, but the tool is simple enough.

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 goes beyond by explaining that '_apiKey' is passed directly to api.anthropic.com and that 'context' aids disambiguation. This adds meaning not fully captured in the schema 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 uses a specific verb ('probe'), identifies the resource ('LLMs'), and specifies the output ('score visibility'). It clearly distinguishes itself from sibling tools like 'scan_competitor_ai_presence' by being more general.

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 concrete use cases ('AI-marketing audits, pre-launch brand checks, competitive monitoring') and explains when to provide API keys. However, it does not explicitly contrast with similar siblings, leaving some room for ambiguity.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively describes key traits: it's a query tool that interprets natural language, selects data sources automatically, and returns results. However, it doesn't mention potential limitations like rate limits, authentication needs, or error handling, leaving some behavioral aspects unspecified.

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 core functionality, followed by practical guidance and examples. Every sentence earns its place: the first explains the purpose, the second describes the mechanism, the third provides usage guidance, and the examples illustrate application. No wasted words, and the structure flows logically from general to specific.

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 (natural language processing to select data sources) and lack of annotations or output schema, the description is reasonably complete. It covers the purpose, usage, and behavioral approach, though it could benefit from mentioning response formats or error cases. The examples help contextualize, but some operational details remain implicit.

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

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

Schema description coverage is 100%, with the single parameter 'question' well-documented in the schema as 'Your question or request in natural language.' The description adds minimal value beyond this, only reinforcing that questions should be in 'plain English' without providing additional syntax or format details. Baseline 3 is appropriate when the schema does the heavy lifting.

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

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

The description clearly states the tool's purpose: 'Ask a question in plain English and get an answer from the best available data source.' It specifies the verb ('ask'), resource ('answer'), and mechanism ('Pipeworx picks the right tool, fills the arguments'), distinguishing it from sibling tools like search_posts or get_profile that require specific parameters and schemas.

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

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

The description explicitly states when to use this tool: 'No need to browse tools or learn schemas — just describe what you need.' It provides clear alternatives by implication (use other tools when you know specific schemas) and includes examples like 'What is the US trade deficit with China?' to illustrate appropriate use cases.

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 extra LLM cost, response format (answer, evidence, refusal reasons), and that it only uses what the tool result contains, going beyond the annotations which already indicate read-only, open-world, idempotent behavior.

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

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

Front-loaded with key phrase 'hallucination-resistant answer mode', every sentence adds value (use cases, behavior, trade-off), though slightly lengthy; nearly optimal.

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 structure (answer, evidence, refusal) and conditions, leaving no major gaps for an agent to understand invocation and expected results.

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

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

Schema coverage is 100% with description of question parameter already in schema; the description adds no new parameter meaning beyond confirming natural language input and alias acceptance, meeting baseline but not adding value.

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

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

The description clearly states it's a 'hallucination-resistant answer mode for high-stakes reads' and explains that it extracts answers only from tool results, distinguishing it from the sibling ask_pipeworx tool.

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

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

Explicitly tells when to use (when answer will be quoted/cited/acted on and agent must not invent facts) and when not to (prefer ask_pipeworx for casual lookups), with specific examples of high-stakes domains.

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 the annotations (readOnlyHint, idempotentHint, etc.), the description extensively details internal behavior: resolver contract (market_match_confidence, alternatives), parent event extractor, news fallback mechanism, safety circuits for low-confidence and closed markets, and wide-spread tradeability warnings. 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 lengthy but well-structured with clear sections (classifiers, fan-out examples, response shapes, safety). The first sentence immediately states the purpose. However, some redundancy exists (e.g., repeating fan-out patterns), and a more concise version could improve readability without losing information.

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

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

Given the complexity and lack of output schema, the description covers all critical aspects: input resolution, fan-out logic with detailed examples, response fields (market, analysis, evidence), and edge cases (low-confidence, closed markets, wide spreads). It provides sufficient information for an agent to understand and 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?

The input schema covers all parameters with descriptions (coverage 100%). The description adds valuable context: how 'market' is resolved (slug/URL/question text), the difference between 'quick' and 'thorough' depth, and the impact of 'include_raw' on response size. This goes beyond the schema definitions.

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

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

The description clearly states the tool's purpose: 'Research a Polymarket bet by pulling the relevant Pipeworx data for it in one call.' It provides specific use cases ('should I bet on X', 'what does the data say about Y', 'is there edge in Z') and lists supported bet classifiers, making it distinct from sibling tools like polymarket_arbitrage or polymarket_edges.

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

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

The description explicitly says when to use the tool ('Use for...') and discusses blocking states for low-confidence matches and closed markets, guiding the agent on result trustworthiness. It does not directly compare with sibling tools, but the use cases are clear enough for an agent to choose appropriately.

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 adds value beyond annotations: it explains handling of off-calendar fiscal years, sorting by primary metric, and that results include paired data with citation URIs. No contradiction with annotations (readOnlyHint=true, openWorldHint=true).

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 somewhat lengthy but each sentence adds value; it is front-loaded with common query patterns and alternatives. Could be slightly tighter, but effectively structured.

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

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

Despite no output schema, the description fully explains the return format (paired data + citation URIs) and covers edge cases like off-calendar fiscal years. It makes the tool's behavior clear for both entity types.

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%, but the description enriches semantics by specifying that type 'company' fetches financial data from SEC EDGAR/XBRL and type 'drug' fetches FAERS data. It also clarifies constraints and examples for the 'values' parameter.

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

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

The description clearly states the tool does side-by-side comparison of 2-5 companies or drugs in a single parallel call, with specific use-case examples like 'which is bigger / better'. It distinguishes from sibling tools by urging preference over 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?

The description explicitly tells when to use (comparing entities) and prefers over sequential lookups. It lacks explicit when-not-to-use instructions, but the context and alternatives are 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?

No annotations are provided, so the description carries the full burden. It discloses that the tool returns 'the most relevant tools with names and descriptions' and has a search function, but lacks details on behavioral traits like rate limits, authentication needs, error handling, or pagination. The description adds some context but doesn't fully compensate for the absence of 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 appropriately sized and front-loaded: the first sentence states the core function, and the second provides crucial usage guidance. Every sentence earns its place with no wasted words, making it efficient and easy to parse.

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

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

Given the tool's moderate complexity (search function with 2 parameters) and no output schema, the description is mostly complete. It explains the purpose, usage context, and return format ('tools with names and descriptions'), but could benefit from mentioning output structure details or limitations. However, it adequately covers the essentials for a search tool.

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

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

Schema description coverage is 100%, so the schema already documents both parameters thoroughly. The description mentions 'by describing what you need' which aligns with the 'query' parameter, but adds no additional semantic context beyond what the schema provides. This meets the baseline for high schema coverage.

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

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

The description clearly states the tool's purpose with specific verbs ('Search the Pipeworx tool catalog') and resources ('by describing what you need'), distinguishing it from sibling tools which focus on social media operations (get_feed, get_followers, etc.). It explicitly identifies the target resource as the tool catalog, making its 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 usage guidelines: 'Call this FIRST when you have 500+ tools available and need to find the right ones for your task.' This gives clear when-to-use criteria (large tool catalog, initial discovery) and distinguishes it from alternatives by positioning it as a preliminary search tool rather than a direct data retrieval tool like the siblings.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint as true and destructiveHint as false. The description adds valuable behavioral context beyond annotations: it lists data sources (SEC EDGAR, XBRL, USPTO, news, GLEIF), mentions a sunset for USPTO PatentsView (soft-fail), and describes the return structure.

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

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

The description is moderately long but well-organized: examples first, then purpose and preference, then data sources and return fields. It is front-loaded and each sentence adds value, though some technical details could be 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 tool's complexity (multi-source aggregation) and absence of output schema, the description provides sufficient detail: it enumerates returned fields (cik, company_name, recent_filings with URIs, fundamentals, patents, news, LEI) and notes limitations (patents soft-fail). No major 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 two parameters. The description adds contextual meaning beyond the schema: clarifies that 'value' accepts ticker or zero-padded CIK, and explicitly states that names are not supported, which the schema does not convey.

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 opens with clear usage examples ('Tell me about X', 'research Acme') and explicitly defines the tool as a 'full cross-source profile of a US public company in ONE parallel call'. It distinguishes this tool from sibling tools by stating it should be preferred over chaining single-source lookups for holistic views.

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 recommends using this tool over alternatives when a holistic view is requested ('ALWAYS PREFER over chaining single-pack ...'). It also provides clear exclusions: names are not supported and advises using 'resolve_entity first if you only have a name'.

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

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

With no annotations provided, the description carries full burden for behavioral disclosure. It states this is a deletion operation, implying mutation/destructive behavior, but doesn't clarify permissions needed, whether deletion is permanent/reversible, error handling (e.g., if key doesn't exist), or side effects. The description adds minimal context beyond the basic action.

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

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

The description is a single, efficient sentence with zero wasted words. It's front-loaded with the core action ('Delete') and resource ('stored memory'), making it immediately scannable and appropriately sized for a simple tool.

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

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

For a destructive tool with no annotations and no output schema, the description is inadequate. It doesn't address critical context like what 'delete' entails (permanent removal?), authentication requirements, error responses, or return values. Given the mutation nature and lack of structured coverage, more behavioral detail is needed.

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

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

Schema description coverage is 100%, with the single parameter 'key' documented as 'Memory key to delete'. The description adds no additional meaning beyond this—it doesn't explain key format, constraints, or examples. Baseline 3 is appropriate since the schema already fully describes the parameter.

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

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

The description clearly states the action ('Delete') and resource ('stored memory by key'), making the purpose immediately understandable. It doesn't explicitly differentiate from sibling tools like 'recall' or 'remember', but the verb 'delete' strongly implies destructive removal versus retrieval or storage operations.

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

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

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention prerequisites (e.g., needing an existing memory key), exclusions, or relationships to sibling tools like 'recall' (which likely retrieves memories) or 'remember' (which likely stores them).

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

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

Annotations already declare read-only, non-destructive, and idempotent behavior. The description adds process details (fetching, extracting, emitting) and output location, providing value beyond annotations.

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

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

The description is concise with 4-5 sentences, front-loading the purpose and process. Every sentence contributes relevant information without redundancy.

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

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

For a tool with 2 parameters and no output schema, the description covers purpose, process, output, and use cases adequately. It could mention error handling but is otherwise complete.

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

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

Schema coverage is 100%, so baseline is 3. The description gives context for the parameters (e.g., 'extracts links') but does not add detailed parameter semantics beyond what the schema's descriptions already offer.

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, explaining the process of fetching and extracting key information. It distinguishes the tool's specific output format (standard llms.txt) but does not explicitly contrast with siblings like ai_visibility_check.

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

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

The 'Useful for' section lists concrete scenarios (client indexing, own projects, competitor auditing), providing clear context for when to use. However, it does not explicitly state when not to use or compare to 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It adds minimal context: the '[Public]' tag hints at accessibility, and the default feed is specified. However, it lacks details on critical behaviors such as rate limits, authentication needs, error handling, or the structure of returned posts, which are essential for a tool that retrieves data.

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

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

The description is brief and front-loaded, efficiently conveying the core purpose and default behavior in a single sentence. However, it could be slightly more structured by separating the public tag from the functional description, but overall, it avoids unnecessary verbosity.

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

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

Given the lack of annotations and output schema, the description is incomplete for a tool that retrieves feed data. It fails to explain what the output looks like (e.g., post format, pagination), any dependencies, or error cases, leaving significant gaps in understanding how to effectively use the tool.

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

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

The input schema has 100% description coverage, clearly documenting both parameters (limit and feed_uri) with defaults and constraints. The description adds no additional parameter semantics beyond what the schema provides, so it meets the baseline score of 3 for adequate but not enhanced coverage.

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

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

The description clearly states the action ('Get posts') and resource ('from a Bluesky feed'), making the purpose understandable. However, it doesn't explicitly differentiate this tool from sibling tools like 'get_posts' or 'search_posts', which appear to retrieve similar content, so it misses the highest score for sibling distinction.

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

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

The description implies usage by mentioning the default feed ('discover/whats-hot'), suggesting this tool is for fetching feed posts rather than other types of content. However, it provides no explicit guidance on when to use this versus alternatives like 'get_posts' or 'search_posts', leaving the context somewhat vague.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It only states the action ('Get a user's followers') without mentioning permissions, rate limits, pagination, or the format of returned data. The '[Public]' prefix hints at accessibility but is vague and insufficient for a tool with no annotation coverage.

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

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

The description is extremely concise—a single, front-loaded sentence that states the core purpose without any wasted words. It efficiently communicates the essential action, making it easy for an agent to parse quickly.

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 lack of annotations and output schema, the description is incomplete. It doesn't explain what the tool returns (e.g., list of followers, metadata), error conditions, or behavioral traits like rate limits. For a tool with two parameters and no structured output, more context is needed to guide effective 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?

The input schema has 100% description coverage, clearly documenting both parameters ('handle' and 'limit') with details like data types, constraints, and defaults. The description adds no additional parameter information beyond what the schema provides, so it meets the baseline score for high schema coverage.

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

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

The description clearly states the tool's purpose with a specific verb ('Get') and resource ('a user's followers'), making it immediately understandable. However, it doesn't differentiate this from sibling tools like 'get_follows' or 'get_profile', which likely retrieve related but different user data, so it doesn't reach the highest score.

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

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

The description provides no guidance on when to use this tool versus alternatives like 'get_follows' or 'get_profile'. It lacks any context about prerequisites, exclusions, or specific use cases, leaving the agent to infer usage from the tool name alone.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It adds minimal context: '[Public]' hints at accessibility but doesn't clarify rate limits, authentication needs, pagination, or response format. For a read operation with no annotation coverage, this leaves significant gaps in understanding how the tool behaves beyond its basic function.

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

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

The description is extremely concise—a single, front-loaded sentence with no wasted words. Every element ('[Public]', 'Get accounts that a user follows') contributes directly to understanding the tool's purpose and scope, making it efficient and easy to parse.

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

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

Given the lack of annotations and output schema, the description is incomplete for effective tool use. It misses critical details like return format (e.g., list structure, fields included), error handling, and how it differs from sibling tools. While concise, it does not compensate for the absence of structured behavioral or output information, leaving the agent under-informed.

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

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

Schema description coverage is 100%, so the input schema fully documents both parameters ('handle' and 'limit') with descriptions and constraints. The description does not add any meaning beyond what the schema provides, such as explaining parameter interactions or usage examples. This meets the baseline score when the schema handles parameter documentation effectively.

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 ('Get') and resource ('accounts that a user follows'), making the purpose unambiguous. However, it does not explicitly differentiate this tool from its sibling 'get_followers', which retrieves the inverse relationship. The '[Public]' prefix adds context about access but doesn't fully distinguish functionality from similar tools.

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

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

No guidance is provided on when to use this tool versus alternatives like 'get_followers' (for followers instead of follows) or 'get_profile' (which might include follow data). The description implies usage for retrieving follow relationships but offers no explicit when/when-not instructions or prerequisites, leaving the agent to infer context from tool names alone.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It indicates this is a read operation ('Get') and public access ('[Public]'), but lacks details on rate limits, authentication needs, pagination, error handling, or what 'recent' means (e.g., time frame). This is inadequate for a tool with potential API constraints.

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

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

The description is a single, efficient sentence with zero waste. It is front-loaded with key information ('[Public] Get recent posts') and appropriately sized for its purpose, making it easy for an agent to parse quickly.

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 annotations and no output schema, the description is incomplete. It fails to explain behavioral traits like rate limits or authentication, and doesn't describe return values (e.g., post format, pagination). For a tool fetching user data with siblings, more context is needed to guide effective 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 description coverage is 100%, so the input schema fully documents both parameters ('handle' and 'limit'). The description adds no additional parameter semantics beyond implying the 'handle' is for a Bluesky user, which is already clear from the schema. Baseline 3 is appropriate as the schema does the heavy lifting.

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

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

The description clearly states the action ('Get recent posts') and target resource ('from a Bluesky user's feed'), with the '[Public]' prefix indicating access scope. However, it doesn't differentiate this tool from sibling tools like 'get_feed' or 'search_posts', which likely serve similar purposes but with different filtering or scope.

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

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

The description provides no guidance on when to use this tool versus alternatives such as 'get_feed' or 'search_posts'. It mentions a specific context ('Bluesky user's feed') but lacks explicit when/when-not instructions or prerequisites, leaving the agent to infer usage based on tool names alone.

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

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

With no annotations provided, the description carries full burden. It discloses the public access nature ('[Public]') and specifies the input format (handle with example), but doesn't describe behavioral traits like rate limits, error conditions, authentication needs, or what data the profile contains. It adds some context but leaves significant gaps.

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

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

The description is a single, efficient sentence that front-loads key information (public access, action, resource, constraint) with zero wasted words. Every element earns its place, making it highly scannable.

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

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

For a simple read operation with 1 parameter and no output schema, the description is adequate but incomplete. It doesn't explain what a 'profile' contains or the response format, which would help the agent understand the tool's output. Given the lack of annotations and output schema, more context would be beneficial.

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

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

Schema description coverage is 100%, so the schema already fully documents the single 'handle' parameter with its type and example. The description adds no additional parameter semantics beyond what's in the schema, meeting the baseline for high coverage.

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

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

The description clearly states the specific action ('Get'), resource ('Bluesky user profile'), and key constraint ('by handle'), distinguishing it from siblings like get_feed or get_posts which target different resources. The inclusion of '[Public]' further clarifies access scope.

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 this tool (to retrieve a user profile by handle) but doesn't explicitly mention when not to use it or name alternatives like resolve_handle (which might convert handles to DIDs). The context is sufficient but lacks explicit exclusions.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the tool is '[Public]', implying accessibility, but doesn't explain what this means operationally (e.g., authentication requirements, rate limits, or data sensitivity). It mentions retrieving a 'post thread' but doesn't describe the return format, error handling, or any side effects. For a tool with no annotations, this leaves significant gaps.

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

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

The description is extremely concise—a single sentence that directly states the tool's purpose. It is front-loaded with the key information ('[Public] Get a post thread by AT URI') and contains no unnecessary words or redundancy. Every part of the sentence serves a clear 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 complexity (a retrieval tool with no annotations and no output schema), the description is incomplete. It lacks details on what a 'post thread' entails, the return format, error conditions, or usage context relative to siblings. The '[Public]' hint is vague without further explanation. For a tool that likely returns structured data, more guidance is needed to be fully helpful.

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, with the single parameter 'post_uri' fully documented in the schema. The description adds no additional meaning beyond what the schema provides (e.g., it doesn't clarify thread-specific aspects of the URI or provide examples). With high schema coverage, the baseline score of 3 is appropriate as the description doesn't compensate but also doesn't detract.

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') and the resource ('a post thread by AT URI'), making the purpose understandable. However, it doesn't explicitly differentiate this from sibling tools like 'get_posts' or 'get_feed', which appear to retrieve similar content. The description is specific but lacks sibling distinction.

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

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

The description provides no guidance on when to use this tool versus alternatives like 'get_posts' or 'search_posts'. It mentions retrieving a 'post thread' but doesn't clarify what constitutes a thread or when this is preferred over other retrieval methods. No exclusions or prerequisites are stated.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, providing a clear safety profile. The description adds that it returns specific fields and distinguishes active vs. cancelled subscriptions via the include_inactive parameter, which aligns with the hints.

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-load the purpose and use case with zero redundancy. Every part adds value without unnecessary elaboration.

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

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

For a simple read-only tool with one optional parameter and no output schema, the description covers purpose, return fields, and usage context. Together with the annotations, it is fully 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% with a well-described optional boolean parameter (include_inactive). The description does not add new parameter details beyond reinforcing the default behavior (active subscriptions). 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 tool's action and resource: 'List the caller's active subscriptions.' It also enumerates the returned fields (id, type, params, etc.), making the purpose specific and distinct 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?

The description provides explicit guidance: 'Use this to review what you're monitoring before adding more or to find an id to cancel.' This tells when to use it meaningfully, though it does not explicitly state when not to use it 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 discloses behavioral traits beyond annotations: it is free, doesn't count against tool-call quota, rate-limited to 5 per identifier per day, and explains how feedback is used by the team. There is no contradiction with annotations.

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

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

The description is concise and well-structured: it starts with the core purpose, then provides usage guidelines, and finally behavioral context. Every sentence adds value without redundancy.

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

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

Given the tool's simplicity (no output schema), the description covers all necessary aspects: purpose, usage, behavior, constraints, and impact. It is fully 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%, but the description adds meaningful context: it explains how to write the message (be specific, 1-2 sentences, 2000 chars max) and elaborates on the type enum values, enhancing understanding beyond the schema.

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

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

The description clearly states the tool is for giving feedback to the Pipeworx team about bugs, feature requests, data gaps, or praise. It distinguishes itself from sibling tools that are about querying data or entities, making its purpose specific and 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 explicitly lists when to use the tool (bug, feature/data_gap, praise) and what not to do (don't paste the end-user's prompt). It also provides context about how the feedback is used and notes rate limits, giving comprehensive usage guidance.

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

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

Annotations already declare safe read-only behavior. The description adds caching details (5min-1h) and data source (CF analytics-engine, no PII), which enriches transparency beyond annotations.

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

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

The description is detailed but not overly verbose. It includes use cases and technical details in a logical order, though could be slightly more concise.

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

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

Despite the lack of an output schema, the description explains what is returned (top tools, packs, call volume) and includes caching and data provenance. It is complete for a simple read-only 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 enum descriptions. The description adds value by explaining the meaning of shorter vs longer windows in terms of use cases, going beyond the schema.

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

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

The description clearly states the tool returns top tools, packs, and call volume over a recent window. It distinguishes itself from sibling tools like discover_tools by focusing on trending usage by AI agents.

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 three explicit use cases, providing good guidance on when to use. However, it does not explicitly mention when not to use or directly compare to sibling tools for exclusion.

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 input requirements (requires one of event or topic, fails otherwise), internal logic (Jaccard similarity threshold, partition filter, placeholders), and response structure. This provides comprehensive behavioral context beyond the read-only, idempotent hints.

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 structured: it opens with a requirement, then covers modes, semantic anchor, partition filter, and response. Each sentence adds value, though slightly verbose for a simple tool. Structure is clear 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?

Despite no output schema, the descriptions fully explain the return format (opportunities array, partition_check object). It covers all necessary aspects: input modes, behavioral conditions, and results. Given the tool's complexity, it is sufficiently complete.

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

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

Schema coverage is 100% with good descriptions. The main description adds significant context: examples of slugs, seed questions, and how each mode works internally, including semantic anchor and partition filter details. This adds meaning 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 finds arbitrage opportunities on Polymarket via monotonicity violations and partition-sum checks. It distinguishes two modes (event and topic) and provides examples, making it distinct from sibling tools like polymarket_edges or polymarket_kalshi_spread.

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 recommends which parameter to use based on the user's need: event for a specific market, topic for cross-event scanning. It also explains that cross-event mode catches patterns missed by single-event mode. However, it does not compare to sibling tools or state when not to use the tool.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false. The description adds extensive behavioral detail: edge calculation (edge_pp_net after slippage), Kelly fractions with caps, 24h-move warnings, caching at KV level for 1 hour, and diagnostics for empty segments. 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 extremely detailed but presented as a single dense paragraph. It contains valuable information but lacks structure (e.g., bullet points or sections), making it harder to parse quickly. While comprehensive, it is not concise.

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

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

Given the tool's complexity (9 parameters, no output schema), the description fully compensates by detailing the response structure (by_segment, fed_candidates, diagnostics), caching behavior, and the logic behind each model family. It leaves no gaps for an intelligent agent to misuse.

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 adequate parameter descriptions. The description adds value beyond schema by explaining the tradeable-edge knobs concept and clarifying that min_partition_leg_kelly applies to per-leg Kelly inside partitions, which is not obvious from 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 the explicit goal of 'what should I bet on today.' It distinguishes itself by detailing three specific model families (model-driven, structural arbitrage, concentrated longshots), which differentiates it from sibling tools 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?

The description implies usage for daily betting discovery and mentions not paging hundreds of markets, but it does not explicitly recommend alternatives like polymarket_arbitrage for pure arbitrage or state when not to use this tool. Context is clear, but explicit exclusions are missing.

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 thorough behavioral details: response structure (leg-by-leg prices, spread, safety fields), two compatibility_warning scenarios, temporal_alignment check, and skipped cross-type/subtype counters. No contradictions with annotations.

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

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

Description is lengthy but well-structured: starts with core purpose, then modes, response details, then safety fields. Some sentences are technical and could be condensed, but the complexity of the tool justifies the length. It front-loads the main idea.

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

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

Without an output schema, the description fully compensates by detailing every response field (leg prices, spread, compatibility_warning, temporal_alignment, skipped counts). It covers all three parameters, including the topic list. The description gives enough for an AI agent to understand inputs, outputs, and edge cases.

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 three parameters. The description adds significant meaning: lists the 10 valid topic shortcuts, explains that explicit tickers override topic-mapped ones, and clarifies that mode selection is via which parameters are provided. This goes well 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?

Description clearly states the tool's purpose: 'Cross-venue spread between Kalshi and Polymarket for the same resolving question.' It explains two modes (topic shortcuts and explicit tickers) and distinguishes from sibling tools that handle intra-venue arbitrage or other comparisons.

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?

Description gives explicit context for when spreads are meaningful (bet shapes equivalent, temporally aligned) and when they are not (compatibility_warning). It advises that pre-mapped topics often return warnings. However, it does not explicitly reference sibling tools as alternatives for specific use cases.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It explains the dual functionality (retrieve by key vs. list all) and persistence across sessions, which is valuable. However, it doesn't mention error handling (e.g., what happens if key doesn't exist), performance characteristics, or format of returned data, leaving some behavioral aspects unclear.

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 perfectly concise with two sentences that each serve distinct purposes: the first explains the dual functionality, and the second provides usage context. There's zero wasted language, and key information 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?

For a tool with 1 parameter, 100% schema coverage, and no output schema, the description provides good contextual completeness. It explains the tool's purpose, usage scenarios, and parameter semantics effectively. The main gap is the lack of output format details, but given the tool's relative simplicity, this is a minor omission.

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

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

The schema has 100% description coverage, so the baseline is 3. The description adds meaningful context by explaining the semantic effect of omitting the key parameter ('omit to list all keys'), which clarifies the tool's dual behavior beyond what the schema's technical description provides.

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

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

The description clearly states the tool's purpose with specific verbs ('retrieve', 'list') and resources ('previously stored memory', 'all stored memories'). It distinguishes from sibling tools like 'remember' (which stores) and 'forget' (which deletes) by focusing on retrieval operations.

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 the tool: 'to retrieve context you saved earlier in the session or in previous sessions.' It also specifies when to omit the key parameter ('omit key to list all keys'), giving clear operational instructions.

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 value by explaining the mark_read behavior (flagging events read for incremental polling) and noting that the feed is persisted. It provides practical context beyond annotations, such as polling suitability and alternative access.

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

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

Four sentences covering purpose, content, filtering, mark_read, and alternative access. Each sentence serves a distinct purpose without redundancy. Could be slightly more concise but overall well-structured and front-loaded with the core action.

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

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

No output schema, but the description lists key fields (source, citation_uri, raw payload). All 5 parameters are documented in the schema. The description adds practical polling guidance and alternative endpoint. Missing details like pagination behavior or rate limits, but 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 description coverage is 100%, so baseline is 3. The description restates filtering (type, since) with an example and rephrases mark_read, but does not add new semantic information 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: 'Pull fired events from your subscription feed.' It specifies the return content (source, citation_uri, raw payload) and distinguishes itself from siblings like get_feed by focusing on alerts/events. The mention of a persistent feed and alternative HTTP endpoint further solidifies its unique role.

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

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

The description implies usage for polling recent alerts and mentions an alternative HTTP endpoint, but does not explicitly state when to use this tool versus siblings like get_feed or list_subscriptions. There is no guidance on when not to use it or prerequisites.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint. Description adds context: fans out to multiple sources, fallback, USPTO soft-fail, and `since` format. No contradiction.

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

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

Single paragraph is dense but clear. Front-loaded with purpose examples. Could be slightly more structured but not verbose.

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

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

No output schema, but description explains return format briefly. Covers sources, fallback, parameter usage. Missing pagination limits, but otherwise complete for the tool's purpose.

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 description adds extra meaning: example queries, explicit `since` formats, and explains value accepts ticker or CIK. Slight improvement over 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 the tool provides a change feed for a company, fanning out to multiple sources (SEC, GDELT/GNews, USPTO). It gives example queries like 'what's new with X' and distinguishes from sibling tool 'entity_profile'.

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

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

Explicitly says when to use entity_profile instead ('when you want the static profile ... regardless of window'). Also explains fallback behavior from GDELT to GNews.

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

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

With no annotations provided, the description carries full burden and does well by disclosing key behavioral traits: it explains persistence differences (authenticated users get persistent memory vs. anonymous sessions lasting 24 hours) and the cross-tool context capability. However, it doesn't mention potential limitations like storage size constraints 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?

The description is perfectly concise with two focused sentences that each earn their place: the first states the core functionality, the second adds important behavioral context about persistence. No wasted words, and it's front-loaded with the primary purpose.

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

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

For a 2-parameter tool with no annotations and no output schema, the description provides good context about what the tool does and its persistence behavior. However, it doesn't explain what happens on success/failure or return values, which would be helpful given the lack of output schema.

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

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

With 100% schema description coverage, the schema already fully documents both parameters. The description doesn't add meaningful parameter semantics beyond what's in the schema (which provides examples and clear descriptions), so it meets the baseline but doesn't enhance understanding of the parameters.

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

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

The description clearly states the tool's purpose with specific verb ('Store') and resource ('key-value pair in your session memory'), and distinguishes it from sibling tools like 'recall' (which presumably retrieves stored data). It explicitly mentions what gets stored and where.

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 this tool ('to save intermediate findings, user preferences, or context across tool calls'), but doesn't explicitly state when not to use it or name alternatives among siblings (though 'recall' is implied as complementary). It gives practical examples but lacks explicit exclusions.

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

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

Annotations already indicate read-only, idempotent, not destructive. The description adds value by explaining that internal cascading of multiple endpoints occurs, that disambiguation is automatic for companies, and that citation URIs are returned. This enriches the behavioral model beyond annotations.

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

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

The description is informative but somewhat verbose, with multiple examples and a bullet-like structure. It is front-loaded with usage examples, which helps. However, it could be trimmed without losing 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 the absence of an output schema, the description adequately explains return values (ticker, CIK, company name, citation URI for company; RxCUI, ingredient, brand, citation URI for drug). It also covers disambiguation and acceptance of different input formats. No major 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% with good parameter descriptions. The description adds context by explaining the meaning of 'value' for each type (e.g., ticker, CIK, or name for company; brand or generic for drug). It also clarifies the return format, which is absent from 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 resolves a name to a canonical ID, with examples like ticker, CIK, RxCUI. The verb 'resolve' and resource 'entity' are specific. However, it does not explicitly differentiate from the sibling 'resolve_handle', which might serve a similar purpose for 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?

The description explicitly says 'Use FIRST whenever you have a name but need an ID.' This provides clear when-to-use guidance. It also mentions that it replaces 2-3 manual lookups, implying efficiency. However, it does not state when not to use or discuss alternatives beyond implied replacement.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the tool is '[Public]', hinting at accessibility, but lacks details on rate limits, error conditions, response format, or whether it's read-only or has side effects. This leaves significant gaps in understanding its behavior.

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

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

The description is extremely concise—a single sentence that front-loads the key information ('[Public]' and the core function). There is no wasted language, making it efficient and easy to parse.

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

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

Given the lack of annotations and output schema, the description is incomplete. It doesn't explain what a DID is, the return format, potential errors, or usage constraints. For a tool with no structured behavioral data, this leaves the agent under-informed about how to effectively 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?

The input schema has 100% description coverage, with the 'handle' parameter well-documented. The description adds no additional parameter semantics beyond what the schema provides, such as handle format examples or validation rules, so it meets the baseline for high schema coverage.

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

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

The description clearly states the specific action ('Resolve') and target resource ('Bluesky handle to a DID'), distinguishing it from sibling tools that fetch feeds, followers, posts, profiles, or search content. It precisely defines the tool's function without redundancy.

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

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

The description provides no guidance on when to use this tool versus alternatives. While it implies usage for handle resolution, it doesn't specify contexts like user lookup or authentication, nor does it mention any sibling tools as alternatives for related tasks.

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, idempotent, and non-destructive. The description adds that it probes with ai_visibility_check and ranks results, which is consistent. It does not contradict annotations and provides additional process context.

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

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

The description is concise, front-loaded with the main purpose, and every sentence adds value. No unnecessary information.

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

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

Given the tool's complexity and the lack of output schema, the description sufficiently explains the process, input constraints (2-8 entities), and output format (ranked list with score, confidence, signal density).

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

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

Schema coverage is 100% with good descriptions. The description adds value by specifying that the first entity is treated as the subject for narrative, which is not in the schema. This extra context justifies a score above baseline.

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

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

The description clearly states the tool compares AI visibility across multiple entities, mentions the use of ai_visibility_check, and specifies the output (ranked list with scores). It effectively distinguishes itself from sibling tools like ai_visibility_check (single entity) and compare_entities.

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

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

The description provides a concrete use case ('competitive AI-marketing audits') and an example question. However, it does not explicitly state when not to use this tool (e.g., for single entity checks use ai_visibility_check) or differentiate from compare_entities.

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

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

Annotations already indicate safe, idempotent, read-only operation. The description adds significant behavioral detail: fans out across services, first measurement delay, partial failures, and graceful degradation. 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 dense but well-structured, front-loading the composite nature and listing output. It is concise yet comprehensive, though slightly long for a single sentence.

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 enumerates return fields, mentions partial failure handling, and covers edge cases like scoped packages. Complete for a composite 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 clear parameter descriptions. The description adds context about version defaults and timing behavior for new versions, providing extra 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?

The description clearly states the tool's purpose as a composite check for adding an npm package, using deps.dev and bundlephobia, and lists the return fields. It distinguishes itself from sibling tools by its specific function, which is unique among the listed siblings.

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

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

Explicitly states when to use: when an agent asks about safety, popularity, size, or cost of adding a package. Also notes NPM-only scope and handles partial failures gracefully, providing clear usage context.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It effectively adds context by specifying authentication requirements ('[Auth required]' and details about bsky_handle and bsky_app_password) and implies it's a read operation (searching), though it doesn't mention rate limits, error handling, or response format. This provides useful behavioral information beyond basic purpose.

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

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

The description is appropriately sized and front-loaded, with two sentences that efficiently convey key information: authentication requirements and the tool's purpose. Every sentence earns its place by providing essential details without unnecessary elaboration or redundancy.

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

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

Given the tool's moderate complexity (search operation with authentication), no annotations, and no output schema, the description is somewhat complete but has gaps. It covers authentication and purpose well but lacks details on response format, error cases, or behavioral constraints like rate limits, which would be helpful for an AI agent to use it 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 schema description coverage is 100%, so the schema already documents both parameters ('limit' and 'query') fully. The description does not add any additional meaning or details about the parameters beyond what the schema provides, such as search syntax or examples. This meets the baseline for high schema coverage.

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

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

The description clearly states the specific action ('Search Bluesky posts by keyword') and identifies the resource ('Bluesky posts'), making the purpose explicit. It distinguishes this tool from siblings like 'get_posts' or 'get_feed' by specifying it's for keyword-based searching rather than retrieval by other criteria.

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 this tool ('Search Bluesky posts by keyword') and mentions authentication requirements, but it does not explicitly state when not to use it or name specific alternatives among the sibling tools. This gives good guidance but lacks explicit exclusions or comparisons.

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

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

Beyond readOnlyHint, openWorldHint, idempotentHint annotations, description discloses character cap (200K), embedding model (BGE-base-en), windowing (500-char overlapping), and output details (offsets, similarity scores). 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?

Well-structured and front-loaded, but slightly verbose with technical details (embedding model) that could be condensed. 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 3 params, no output schema, description fully explains inputs, behavior, output, limitations, and embedding approach. Complete for 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 covers 100% of parameters; description adds examples for query and clarifies max chars for text, enhancing 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?

Clearly states 'Semantic search INSIDE a fetched record' with specific verb and resource. Distinguished from sibling ask_pipeworx_grounded by explaining the pairing workflow.

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

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

Explicitly says 'Use when the record is too big to cram into the prompt' and pairs with ask_pipeworx_grounded, providing clear when-to-use guidance and alternative.

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 includes 'Create ... subscription' which is a write operation, but annotations set readOnlyHint: true, creating a direct contradiction. Per rules, score 1 for contradiction. The description does add behavioral context (OAuth requirement, delivery caps) but the contradiction overrides.

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

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

The description is concise and well-structured. It front-loads the core purpose, then provides necessary details on type, parameters, requirements, and delivery. Every sentence adds value without redundancy.

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

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

Given the tool's complexity (3 parameters, nested objects, no output schema), the description covers requirements, parameter usage, delivery options, limitations, and return value. It leaves no major gaps for an agent to select and invoke the tool correctly.

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

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

Schema coverage is 100%, so baseline is 3. The description adds significant meaning: explains type enum values, provides example params (ticker, items) and defaults, details delivery channels with examples and limitations (SMS cap). This exceeds the schema's minimal 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 'Create a proactive monitoring subscription to a live-data event stream.' It specifies the supported type (sec_8k) and provides concrete examples of filtering. It distinguishes from sibling tools like list_subscriptions (list) and unsubscribe (remove) 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 context on when to use: requires Pipeworx OAuth account, v1 only supports sec_8k, and explains delivery channels. However, it does not explicitly state when not to use or contrast with alternatives like list_subscriptions for viewing or unsubscribe for removal.

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 contradicts the annotations: it describes a mutation (cancel, deactivate) while annotations set readOnlyHint=true. This contradiction severely undermines transparency, despite the description adding valid behavioral details.

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

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

Two clear sentences with no redundant information. Every part serves a purpose: action, constraint, effect, and consequence.

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

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

For a simple tool with one parameter and no output schema, the description covers purpose, ownership, and consequences (deactivation, availability via recent_alerts). Lacks detail on error handling or idempotency, but annotations fill some gaps.

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

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

Schema coverage is 100%, so baseline is 3. The description adds little beyond the schema's parameter description ('Subscription id (uuid) returned by subscribe').

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 'Cancel a subscription by id', specifying the verb 'Cancel' and the resource 'subscription'. It distinguishes itself from siblings like 'subscribe' and 'list_subscriptions'.

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

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

Explicitly mentions ownership enforcement ('you can only cancel your own subscriptions'), which guides usage. However, it does not explicitly state when not to use this tool in favor of alternatives, though the 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 indicate safe, idempotent, read-only behavior. The description adds value by detailing the return format (verdict, structured form, actual value with citation, percent delta) and noting that it replaces 4-6 sequential calls. 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 relatively concise, with key information front-loaded. It could be slightly more structured (e.g., bullet points), but every sentence provides useful information.

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

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

Given the tool has one parameter and no output schema, the description provides sufficient context: what it does, when to use, and what it returns. It does not cover error cases or limitations, but the combination of annotations and description is adequate.

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

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

Schema coverage is 100% with a single parameter 'claim' that already has a descriptive schema description. The tool description reiterates this and provides examples, but adds little beyond the schema. Baseline 3 is appropriate.

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

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

The description clearly states the tool's purpose: natural-language claim verification. It provides explicit trigger phrases like "Is it true that…" and specifies its domain (company-financial claims via SEC EDGAR + XBRL). This differentiates it from sibling tools, which are unrelated.

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

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

The description explicitly says when to use the tool: "whenever the agent needs to check whether something a user said is factually correct." It gives examples of appropriate claims. It does not mention when not to use, but the domain specificity implies it is not for other types of claims. No alternative tools are named, but the tool's specialization makes this less critical.

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