The Graph

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

Annotations already indicate read-only, idempotent, non-destructive. The description adds value by disclosing the default free model, the need for a BYO API key for Anthropic with direct payment to Anthropic, and the return structure (per-model {score, confidence, signals, raw_response} + combined view). This goes beyond annotations.

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

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

The description is two sentences plus a use-case sentence. It is front-loaded with the core action, and every sentence adds value. No fluff or repetition.

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

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

Given 4 parameters and no output schema, the description adequately covers the return structure and use cases. It could benefit from more detail on scoring methodology or limitations, but overall it is sufficient for an AI agent to understand the tool's capabilities.

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

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

Schema coverage is 100%, but the description adds context beyond the schema: default model is Workers AI Llama-3.3-70b (free), _apiKey is only needed if Anthropic is in models, and context helps disambiguate. This enhances understanding of parameter usage.

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

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

The description clearly states the tool probes LLMs for knowledge about an entity and scores visibility (0-100) per model. It specifies the default model and the ability to add Anthropic. This distinguishes it from sibling tools like entity_profile and scan_competitor_ai_presence.

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

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

The description gives clear use cases: AI-marketing audits, pre-launch brand checks, competitive monitoring. It explains required input (entity) and optional parameters (models, _apiKey, context). However, it doesn't explicitly contrast with alternatives or state when not to use.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds value by explaining that the tool dynamically routes to 3,775 tools and returns structured answers with stable citation URIs, offering insight into its behavior beyond the 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: it front-loads with a strong usage directive, lists domains, explains the routing mechanism, and provides examples. Every sentence earns its place, and the length is appropriate for the tool's complexity.

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

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

Given the tool has no output schema, the description mentions the return of 'structured answer with stable pipeworx:// citation URIs', which is useful. It covers key aspects but could further clarify the output format or explicitly differentiate from siblings like deep_research. Overall, it is sufficiently complete for the context.

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

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

The input schema has 100% coverage with a clear description for each parameter (all aliases for 'question'). The description does not add parameter-specific details beyond the schema. Baseline is 3 for high coverage, and no extra semantic value is provided.

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 function: it routes questions to a large set of verified sources and returns structured answers with citation URIs. It lists specific domains (SEC filings, FDA data, etc.) and distinguishes itself from web search, making the purpose highly specific and actionable.

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

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

The description explicitly advises preferring this tool over web search for factual questions and provides concrete examples of when to use it ('what is', 'look up', etc.). It also notes that web search could be used but this is preferable. However, it does not explicitly compare to sibling tools like ask_pipeworx_grounded or deep_research, which would be helpful.

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

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

The description adds significant behavioral context beyond the annotations. It describes the return structure with explicit refusal types (not_in_source, no_tool_match, tool_error, data_truncated, llm_error). It also notes the extra LLM call cost. Annotations already indicate readOnly, openWorld, idempotent, non-destructive, and there is no contradiction.

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

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

The description is front-loaded with the core purpose and is structured logically. It is slightly verbose but every sentence adds value. Slight reduction could improve conciseness, but it remains clear and comprehensive.

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 (routing to 3,775 sources, multiple refusal reasons) and the absence of an output schema, the description is impressively complete. It details the return format, failure modes, and use-case contexts, leaving no critical gaps for an agent.

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

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

Schema description coverage is 100%, so the baseline is 3. The description lists multiple aliases for the question parameter, which adds marginal value beyond the schema. No further parameter semantics are provided, which is acceptable given the schema's completeness.

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: 'Hallucination-resistant answer mode for high-stakes reads.' It specifies the same routing as ask_pipeworx but with extraction using only tool result content. It also distinguishes from its sibling by noting the extra LLM call cost and the appropriate use cases.

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

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

The description explicitly states when to use this tool: 'Use whenever an answer will be quoted, cited, or acted on, and the agent must not invent facts.' It also provides a clear alternative: 'prefer ask_pipeworx for casual lookups.' This provides excellent guidance on tool selection.

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

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

Annotations already declare readOnly, idempotent, and non-destructive. The description adds a wealth of behavioral details: market resolution, classifier fan-out, response shapes, resolver contract with confidence levels, parent event extraction, news fallback, safety short-circuits, and cancellation rule parsing. This far exceeds what annotations provide.

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

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

The description is comprehensive but very long and encyclopedic. While the information is valuable, it could be more structured and front-loaded. Every sentence earns its place, but the length may overwhelm an AI agent scanning for key details.

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 explains return values (market, analysis, evidence, resolver contract) and covers edge cases (low-confidence matches, closed markets, wide spreads, cancellation rules). This ensures the agent knows exactly what to expect.

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 and already explains each parameter (market, depth, include_raw). The description reiterates the market input types but does not add significant new meaning 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 'Research a Polymarket bet by pulling the relevant Pipeworx data for it in one call' and provides typical use cases like 'should I bet on X'. This distinguishes it from sibling tools like polymarket_edges, which focus on finding opportunities across markets.

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 use cases ('Use for ...') and provides extensive context on behavior (fan-out, response shapes, safety mechanisms). However, it does not explicitly compare to siblings or state when not to use this tool, so it loses a point for lack of 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 safe, read-only, idempotent behavior. The description adds valuable context: it pulls LATEST 10-K data, handles off-calendar fiscal years, returns specific financial metrics, sorts by primary metric, and includes citation URIs. This 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 a single paragraph but highly efficient. It starts with query examples, defines core function, details type-specific behavior, then explains sorting and output format. Every sentence adds value; no fluff.

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

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

Given there is no output schema, the description still covers return data (paired data, citation URIs), sorting logic, and data sources for each entity type. It is complete enough for an AI agent to understand what to expect.

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 meaning by explaining what each type returns (company vs. drug) and the expected format of values (tickers/CIKs for companies, names for drugs). It also notes maxItems and minItems, reinforcing schema constraints.

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

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

The description explicitly states the tool's purpose: side-by-side comparison of 2-5 companies or drugs. It gives example queries and specifies data sources (SEC EDGAR/XBRL for companies, FAERS/FDA/clinical trials for drugs). It also distinguishes itself from sequential single-pack 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 provides explicit guidance: 'ALWAYS PREFER over sequential single-pack lookups when comparing entities.' It also explains when to use this tool (comparing entities) and why it is more efficient (replaces 8-15 sequential lookups).

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

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

Annotations already provide readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false. The description adds context on non-invented answers (gaps[]), citations, parallel execution, timing (15-60s), and account requirements.

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

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

Well-structured, front-loaded with core capability. Sentences are dense with information covering process, usage, requirements, and timing. Could be slightly more concise but every sentence adds value.

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

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

Despite no output schema, the description fully describes the return format (findings packet with evidence, confidence, source, fetched_at, citations, gaps). Covers account requirements, timing, and alternative tools. Complete for a complex research tool.

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

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

Schema coverage is 100% (baseline 3). Description adds meaning by explaining 'depth' values (quick=3, standard=5, thorough=8 facets) and that thorough requires paid plan. Also clarifies that the question can be broad/multi-part.

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 'Grounded multi-source research in ONE call' and details the decomposition and parallel routing process. It distinguishes itself from sibling tool 'ask_pipeworx' which is for single lookups.

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

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

Explicitly advises using this tool for broad/multi-part questions and recommends 'ask_pipeworx' for single lookups. Also mentions account requirements and plan limitations for 'thorough' depth.

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

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

Annotations already declare readOnlyHint=true and idempotentHint=true, so safety profile is clear. Description adds context about returning top-N relevant tools with full schemas and being ready to call directly, which provides useful behavioral context 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?

Description is front-loaded with purpose and usage, but the long list of domains adds some verbosity. Still, every sentence serves a purpose, and the structure is logical.

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 parameter count, schema coverage, and lack of output schema, the description fully covers what the tool does, how to use it, and what to expect in return. It explains the return format (names, descriptions, schemas) and that results are ready to call.

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 value by clarifying that multiple parameter names (task, q, description, search) are aliases for the main query parameter. Examples in the schema also help. This enhances understanding 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?

Description clearly states 'Find tools by describing the data or task' and specifically distinguishes this tool from siblings by noting it is for discovery of tools themselves, not for performing other tasks. It lists many domains, giving a clear sense of 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?

Explicitly says 'Call this FIRST when you have many tools available and want to see the option set (not just one answer).' Also enumerates many domains where this tool is applicable, providing clear when-to-use guidance.

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

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

Annotations already indicate readOnly, openWorld, idempotent, and non-destructive hints. The description adds valuable behavioral context: the tool fans out across multiple sources in parallel, returns specific fields, and mentions soft-fail for patents due to API sunset. 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 somewhat lengthy but well-structured and front-loaded with example queries. Every sentence adds useful information, though it could be slightly more concise without losing clarity. No wasted words.

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

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

For a complex tool with no output schema, the description thoroughly explains what is returned: CIK, company name, recent filings with URIs, fundamentals sorted by period, patent status, news fallback, and LEI. It also addresses edge cases like patent soft-fail and name resolution. Complete for the agent to understand capabilities and limitations.

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

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

Schema coverage is 100% with descriptions for both parameters. The description adds further value by providing concrete examples (e.g., 'AAPL', '0000320193') and clarifying that names are not supported. This goes beyond the schema, but the schema already does a good job, so a 4 is fitting.

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 provides a 'full cross-source profile of a US public company' and lists example queries like 'Tell me about X' or 'brief me on Tesla'. It distinguishes itself from siblings like resolve_entity by specifying that names are not supported and to use resolve_entity first. This makes the 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 says 'ALWAYS PREFER over chaining single-pack SEC/XBRL/news lookups when the user asks for a holistic view', giving clear when-to-use guidance. It also states when not to use (names not supported) and directs to resolve_entity as an alternative. This provides excellent context for the agent.

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

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

Annotations already mark destructiveHint=true and readOnlyHint=false, so description's 'Delete...' adds minimal extra. It adds context about clearing sensitive data but doesn't discuss error handling or irreversibility beyond what annotations imply.

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

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

Three sentences, each earning its place: action, usage guidance, sibling pairing. No redundancy.

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

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

For a simple 1-parameter destructive tool with no output schema, the description covers purpose, usage, and safety context sufficiently. No gaps.

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

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

Schema coverage is 100% with parameter 'key' described as 'Memory key to delete.' Description adds no further meaning beyond the schema, meeting 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 'Delete a previously stored memory by key.' It uses a specific verb and resource, and implicitly distinguishes from sibling tools 'remember' and 'recall' as the deletion counterpart.

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 context is stale, the task is done, or you want to clear sensitive data.' Also pairs with siblings. Does not explicitly state when not to use, but provides clear context.

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

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

Annotations already indicate read-only, idempotent, non-destructive behavior. The description adds behavioral details: fetches page, extracts title/description/key links, emits standard markdown format. No contradictions.

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

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

The description is two concise sentences plus a use-case list. Every sentence adds value, with no fluff or repetition. Front-loaded with core action and 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 tool's simplicity (2 parameters, no output schema), the description covers purpose, inputs, output format, and use cases adequately. No missing information for effective agent invocation.

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

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

Schema coverage is 100%, so baseline 3. The description mirrors schema descriptions for 'url' and 'max_links' without adding new semantic information. No additional constraints or examples beyond defaults.

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

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

The description clearly states the verb 'generate' and the resource 'llms.txt file for any URL'. It distinguishes from sibling tools like 'scan_competitor_ai_presence' by focusing on generating the file for AI crawler indexing.

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

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

The description provides explicit use cases: getting a client's site indexed by AI, drafting llms.txt, or auditing competitor AI visibility. It lacks explicit when-not-to-use or alternatives among siblings, but the contexts 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?

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds specific output details (types, fields, arguments) but omits other behavioral aspects like rate limits. Overall good transparency with annotations.

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

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

Two concise sentences with no redundancy. Front-loaded with the core action and output, every word earns its place.

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

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

The tool is simple with one parameter and an output schema. The description, combined with annotations and schema, provides all necessary context for an agent to use it effectively.

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

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

Schema coverage is 100% for the single parameter 'subgraph_id', described as 'Subgraph deployment ID'. The description only restates the context without adding new semantics beyond the schema, so baseline 3 is appropriate.

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

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

The description clearly states the verb 'fetch', the resource 'subgraph's GraphQL schema', and the specific output 'types, fields, and arguments'. It effectively distinguishes from sibling tools like 'query_subgraph' which executes queries.

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

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

The description implies the tool is for building queries by obtaining the schema, but does not explicitly state when not to use it or provide alternatives. However, the context of siblings provides some guidance.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds value by listing the returned fields (id, type, params, etc.), providing behavioral context beyond annotations.

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

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

Two sentences with no fluff: the first states purpose and return, the second gives usage guidance. 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?

Despite no output schema, the description explains return fields. It covers purpose, usage, and parameter context sufficiently for an AI agent to use effectively.

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

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

Schema coverage is 100% with the 'include_inactive' parameter described. The description implicitly relates by stating 'active subscriptions', adding context for the default behavior and parameter usage.

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

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

The description clearly states the verb 'List' and the resource 'the caller's active subscriptions', and distinguishes from sibling tools like subscribe and unsubscribe by specifying the action and return fields.

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

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

The description explicitly advises using it to review monitoring before adding more or to find an id to cancel, providing clear context. It does not mention exclusions or alternatives but effectively guides when to use.

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

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

Discloses rate limit (5 per identifier per day), free usage, and that it doesn't count against quota. Adds value beyond annotations (which only show non-destructive etc.). 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?

Three sentences, front-loaded with purpose, then usage, then behavioral info. No waste.

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

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

Complete for a feedback tool: covers purpose, usage, behavioral constraints, and parameter guidance. No output schema needed; feedback is sent server-side.

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

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

Schema coverage is 100%, so baseline is 3. Description adds value by giving examples for 'type' and explaining the context object's purpose, plus constraints on message content. Not fully detailed but adequate.

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

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

Clearly states it is for sending feedback to the Pipeworx team, with explicit types (bug, feature, data_gap, praise). Distinguishes from sibling tools by being a feedback mechanism.

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

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

Provides explicit when-to-use scenarios (bug, feature/data_gap, praise) and a clear instruction not to paste end-user prompts. No ambiguity.

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

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

Annotations already declare safe traits (readOnlyHint, idempotentHint, etc.), but the description adds substantial behavioral context: self-aggregating signal from analytics, no PII, caching behavior (5min-1h), and how different windows affect results. No contradictions with annotations.

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

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

The description is concise with two well-crafted sentences and a bullet list of use cases. Every part adds value: purpose, what it returns, usage scenarios, and caching details. No wasted words.

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

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

Given the tool has no output schema, the description adequately explains the return value (top tools, top packs, total call volume) and window options. Combined with annotations, it provides complete context for an agent to invoke the tool correctly.

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

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

Schema coverage is 100% for the single parameter 'window'. The description adds semantic meaning beyond the enum by explaining that shorter windows surface hot trends and longer windows show steady-state demand, providing actionable guidance.

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: revealing what other AI agents are calling on Pipeworx, including top tools, top packs, and call volume. It uses a specific verb ('Returns') and resource ('tools, packs, call volume'), distinguishing it from sibling tools like discover_tools or ask_pipeworx.

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

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

The description explicitly lists three use cases (discovering hot data sources, confirming canonical choices, aligning use cases), providing clear context for when to use the tool. While it doesn't mention when not to use it, the listed use cases implicitly differentiate it from alternatives.

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

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

The description adds substantial behavioral context beyond annotations: it explains the underlying logic (Jaccard similarity threshold, partition placeholder filter, fill check against depth). Annotations indicate readOnly and idempotent, and the description confirms non-destructive nature. 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 detailed but each sentence provides unique information. It is front-loaded with the requirement and main purpose. It could benefit from bullet points for readability, but it remains clear and efficient.

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

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

Given the tool's complexity (no output schema, two simple parameters), the description covers input constraints, behavior, and return structure (opportunities, partition check, fill check). It even references sibling tool polymarket_fill_risk for custom sizing. Minor omission: no explicit mention of return types, but description text compensates.

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 significant meaning beyond parameter names and descriptions. It provides examples of valid inputs ('fed-decision-may-2026'), explains the effect of each parameter on mode, and describes how output differs by mode.

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

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

The description clearly specifies the tool's function: finding arbitrage opportunities on Polymarket via monotonicity violations and partition-sum checks. It distinguishes two modes (event and topic) with precise examples, and the verb 'Find arbitrage opportunities' is specific to this resource.

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

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

The description explicitly states the requirement to provide one of `event` or `topic` and explains when each mode is appropriate: event for a specific market, topic for cross-event scanning. It notes that cross-event mode catches patterns single-event misses, but does not provide explicit 'when not to use' or alternatives.

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

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

Annotations already indicate readOnlyHint, idempotentHint, and non-destructive nature. The description adds value by detailing caching ('Cached 1h at the KV level'), internal model behavior, and tradeable-edge knobs. 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 well-structured with clear segments and bullet points, but is verbose (multiple paragraphs). While most sentences add technical value, the length could be reduced for faster agent parsing. Some redundancy exists (e.g., 'edge_pp_net (after slippage)' already implied in min_edge_pp description).

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 the response structure (by_segment, top-level fields, diagnostics), caching behavior, edge cases (Fed bets), and knob interactions. It leaves no major gaps for agent invocation.

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

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

Schema coverage is 100% with well-described properties. The description adds extra context beyond schema (e.g., 'edge net of slippage', 'Bump for very thin partitions', default explanations), helping agents understand parameter impact and trade-offs.

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 scans Polymarket markets and returns opportunities where Pipeworx data disagrees with market price. It distinguishes itself from siblings by detailing unique model families (MODEL_DRIVEN, STRUCTURAL_ARBITRAGE, CONCENTRATED_LONGSHOT), but does not explicitly compare to 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 via 'Built for "what should I bet on today"' and mentions Fed bets are excluded from ranking, but lacks explicit when-not scenarios or alternatives (e.g., no comparison to polymarket_edge_tracker or polymarket_kalshi_spread). Usage context is clear but exclusions are not comprehensive.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint. Description adds return format details (tracked, expired, snapshot_dates) and limitations (60-day TTL, daily closes, not intraday), providing additional behavioral context 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?

Description is front-loaded with a key question, then structured into clear sections (RESPONSE details, LIMITS). Every sentence provides unique information without redundancy, making it efficient and well-organized.

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

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

With no output schema, the description thoroughly explains return fields (tracked[], expired[], snapshot_dates[]), their subfields (first_seen, trend, decay_pp_per_day, lifespan_days), and limitations (60-day TTL, daily closes). It covers all needed context for an agent to understand usage and output.

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% (both parameters described). The tool description enhances with defaults (days default 14, window default '1wk'), clamping (days clamp 2-30), and window options (24hr, 1wk, 1mo), adding value beyond the schema alone.

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

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

Description clearly states it provides 'edge persistence and decay telemetry' from daily snapshots, answering a specific question about edge duration. It distinguishes from sibling tools like polymarket_edges (current edges) by focusing on historical persistence.

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

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

Usage context is implied through the example of fresh vs. old wide edges, and parameters (days, window) are explained. However, no explicit mention of when to use over specific siblings, though the purpose makes it 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 readOnly, openWorld, idempotent, not destructive. The description adds detailed behavioral context: it walks the ladder, returns specific fields (top_of_book, vwap_fill_price, slippage_pp, shares_filled, max_fillable_usd, verdict), and warns about partial basket fills converting arb into directional positions - the dominant loss mode. No contradiction.

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

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

The description is fairly long but well-organized: overall purpose, required parameter note, single-market mode details, basket mode details, and usage guidance. Every sentence adds value. Could be slightly tightened but remains efficient.

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

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

Given the tool's complexity (two modes, multiple return fields), the description is highly complete. It lists all key outputs (top_of_book, vwap_fill_price, slippage_pp, shares_filled, max_fillable_usd, verdict) and explains the verdict options. It also covers the critical risk of partial basket fills. No output schema exists, but the description compensates fully.

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

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

Schema description coverage is 100%, so baseline is 3. The description adds significant value beyond the schema: it explains the dual role of 'market' vs 'event' for single/basket modes, elaborates on 'size_usd' interpretation (max spend vs target proceeds vs settlement notional), and clarifies the automatic default for 'side' in basket mode. This justifies a 4.

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

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

The description clearly states the tool checks realizable vs theoretical edge against live CLOB order-book depth, and it distinguishes between single-market and basket modes. It explicitly positions itself relative to sibling tools like polymarket_arbitrage and polymarket_edges, making its purpose unmistakable.

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

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

The description explicitly says 'USE THIS before acting on any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500'. It explains why (theoretical overround on thin books not capturable, partial baskets create directional risk), providing clear when-to-use and when-not-to-use guidance.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint as false. The description adds significant behavioral detail beyond annotations: compatibility_warning conditions, temporal alignment, skipped cross-type/subtype counters, and the fact that cross-venue spreads are rarer than the shortcut list suggests. No contradiction with annotations.

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

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

The description is well-structured with sections for modes, response fields, and safety fields. It is front-loaded with the core purpose. While somewhat long, every sentence adds value, explaining edge cases and behavior. Could be slightly trimmed without losing key 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?

No output schema exists, so the description must fully explain return values. It covers leg-by-leg prices, matched spread top_spreads_pp, and all safety fields (compatibility_warning, temporal_alignment, skipped counters). Given the tool's complexity (two venues, two modes, compatibility logic), the description is comprehensive and leaves no critical gap.

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 all three parameters described. The description adds value by listing all 10 topic shortcuts, explaining that explicit tickers override mapped sides, and providing examples. This goes beyond the schema's property 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 explicitly states 'Cross-venue spread between Kalshi and Polymarket for the same resolving question,' clearly identifying the verb (spread computation) and resource (cross-venue). It distinguishes from all sibling tools, as none appear to compute spreads between these two prediction markets.

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

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

The description explains two modes (topic shortcuts or explicit IDs) and provides explicit guidance on when spreads are tradeable vs. when compatibility_warning fires (e.g., non-equivalent bet shapes, temporal misalignment). It warns that pre-mapped topics often return warnings and states 'pre-mapped ≠ tradeable', giving clear when-to-use and when-not-to-use cues.

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 non-destructive. The description adds the return structure ('GraphQL data block plus any errors'), which is useful beyond the annotations. No contradictions.

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

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

The description is two sentences, front-loaded with the purpose, and provides essential details without redundancy. Every sentence earns its place.

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

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

Given the annotations (readOnly, idempotent) and the output schema (though not shown), the description covers the subgraph ID format, optional variables, and return content. It is sufficient for this GraphQL query 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%, with each parameter documented. The description adds value by explaining subgraph_id format ('starts with Qm… or 0x…') and the inclusion of errors in returns, which is not in the schema.

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

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

The description specifies the action ('Run a GraphQL query'), the resource ('a subgraph on The Graph network'), and the return format. It clearly distinguishes from sibling tools, none of which are related to GraphQL subgraph queries.

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

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

The description provides context on subgraph_id format and where to look up IDs (thegraph.com/explorer). It implies usage for querying on-chain data, but does not explicitly state when not to use or mention alternatives, though none are apparent among siblings.

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

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

Annotations (readOnlyHint, idempotentHint, destructiveHint) are consistent. Description adds scoping ('Scoped to your identifier') beyond annotations. Does not detail behavior on missing keys or rate limits, but adequate for a simple read tool.

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

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

Three concise sentences, front-loaded with main purpose, each sentence adds value. No redundancy or fluff.

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

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

Covers core behavior, scoping, and pairing with siblings. No output schema exists, so return format is not explained; slight gap on missing key behavior, but overall sufficient for a simple retrieval tool.

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

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

Schema coverage is 100% and parameter description in schema matches tool description. Description adds no new parameter information beyond schema, so baseline 3 is appropriate.

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

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

Description clearly states 'Retrieve a value previously saved via remember, or list all saved keys', specifying verb (retrieve) and resource (saved value). Distinguishes from siblings 'remember' and 'forget' by explaining their pairing.

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 to look up context the agent stored earlier' and pairs with remember/forget. Does not explicitly state when not to use, but the context implies retrieval-only and scoping is mentioned. Good guidance but not exhaustive.

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. The description adds valuable behavioral context about the mark_read flag updating read status, the output fields, and that the feed is also accessible via URL, without contradicting annotations.

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

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

Concise single paragraph with front-loaded purpose, followed by output details, filtering, mark_read behavior, and polling note. Every sentence adds value with no redundancy.

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

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

Despite no output schema, the description explains the return fields (source, citation_uri, raw payload). It covers filtering, state management via mark_read, and alternative access. Missing explicit mention of pagination (limit is in schema) but overall complete for this tool's complexity.

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

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

Schema description coverage is 100%, so baseline is 3. The description adds extra semantics like example filter type 'sec_8k' and explains that mark_read:true affects subsequent calls, which goes beyond 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 clearly states that the tool pulls fired events from the subscription feed, specifies the output includes source, citation_uri, and raw event payload, and distinguishes it from sibling tools like list_subscriptions or subscribe by focusing on alerts retrieval.

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

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

Provides guidance on filtering by type and since, explains mark_read behavior, notes that polling works, and mentions an alternative HTTP endpoint. However, it does not explicitly state when not to use this tool versus alternatives.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint=false. Description adds substantial behavioral context: fans out to multiple sources, fallback logic, API sunset for USPTO, return structure with changes[] and citation URIs, and accepts date or relative shorthands.

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 relatively long but well-structured: examples first, then details on data sources, parameter formats, and return structure. Every sentence adds value; could be slightly more concise but remains clear.

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

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

Despite no output schema, the description explains the return structure (changes[] grouped by source, total_changes count, pipeworx:// URIs). It also covers edge cases like USPTO soft-fail and GDELT→GNews fallback, making it complete for a multi-source aggregation tool.

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

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

Schema coverage is 100% and already describes parameters. Description adds value by giving concrete examples for 'since' (ISO dates, relative shorthands like '7d', '30d'), explaining valid inputs for 'value' (ticker or CIK), and clarifying the 'type' is limited to 'company'.

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

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

Description specifies a clear verb-resource pair ('change feed for a company') with explicit query examples ('What's new with X'), and distinguishes from sibling tool entity_profile by stating when to use the static profile instead.

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

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

Provides explicit guidance on when to use this tool (e.g., 'recent changes' queries) and when not to (use entity_profile for static profile). Also describes fallback behavior between GDELT and GNews, and notes USPTO soft-fail until reactivated.

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 idempotent, non-destructive, and non-read-only traits. Description adds context on session scoping and persistence duration (24 hours for anonymous, persistent for authenticated). 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?

Three sentences, front-loaded with purpose, no wasted words. Covers key points efficiently.

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 behavior implicitly via pairing with recall. Covers persistence, scoping, and usage context adequately for a simple memory tool.

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

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

Schema coverage is 100% with good descriptions for key and value. Description adds general context ('key-value pair scoped by identifier') but doesn't significantly enhance parameter details beyond schema.

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

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

Description clearly states verb (save), resource (data), and distinguishes from siblings (recall, forget). Specific examples provided (resolved ticker, target address).

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

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

Explicitly says when to use ('when you discover something worth carrying forward') and pairs with recall/forget. Also notes differences in persistence for authenticated vs anonymous users.

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

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

Annotations already indicate readOnly, openWorld, idempotent, and non-destructive traits. The description adds valuable context: internal cascading lookups, auto-disambiguation, and citation URI returns, which align with and extend the 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, starting with query examples, then stating the primary use case, followed by clear type breakdowns. Every sentence adds value, and no extraneous information is present.

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 return values for each type, including citation URIs. The tool's role as a first-step resolver is thoroughly covered, making it complete for the given complexity.

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

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

Schema coverage is 100%, and the description enriches both parameters with examples and return details (e.g., company returns ticker+CIK+name+URI, drug returns RxCUI+ingredient+name). This adds significant meaning beyond schema.

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

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

The description clearly defines the tool's purpose: resolving user-spoken names to canonical identifiers. It uses specific verbs ('resolve') and examples ('ticker', 'CIK', 'RxCUI'), and emphasizes using it first, making its role distinct among 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?

It explicitly states 'Use FIRST whenever you have a name but need an ID.' It also explains that it replaces manual lookups. However, it does not provide when-not-to-use or compare with sibling tools like 'entity_profile' or 'compare_entities'.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint as false/safe. The description adds value by describing the probing mechanism, ranking, and output fields (score, confidence, signal density). It doesn't contradict annotations and provides useful context beyond them.

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

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

The description is front-loaded with the main purpose in two sentences, followed by a contextual example and an explanation of the output format. Every sentence is informative without redundancy, maximizing clarity in a compact form.

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?

There is no output schema, so the description must cover return values, which it does: 'ranked list with score, confidence, signal density per entity.' It also explains the underlying mechanism (calling ai_visibility_check) and provides a usage example, making it comprehensive for the tool's complexity.

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

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

Schema coverage is 100% with descriptions for all four parameters. The description adds extra meaning: it explains that the first entity is the 'subject' for narrative and that the context parameter is applied to every probe. This goes beyond the schema's basic descriptions.

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

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

The description clearly states the tool compares AI visibility across multiple entities side-by-side, using a specific verb ('compare') and resource ('AI visibility across entities'). It distinguishes itself from sibling tools like ai_visibility_check (single entity) and compare_entities (generic comparison) by explicitly mentioning it probes each entity with ai_visibility_check and returns a ranked list.

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

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

The description provides a clear use case: 'competitive AI-marketing audits' with an example question. While it doesn't explicitly state when not to use, the context implies it's for multiple entities and is an aggregation of ai_visibility_check. The example clarifies the intent.

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

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

Discloses important behavioral traits: partial failures with graceful degradation, 5-30s delay for bundlephobia first measurement, and the 'sources_failed' field. Adds value beyond annotations which already indicate readOnlyHint and idempotentHint.

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 with front-loaded purpose, every sentence provides essential information: composite nature, data sources, usage guidance, ecosystem scope, failure behavior. No wasted words.

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

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

Despite no output schema, description lists all returned fields (is_latest, license, etc.) and explains partial failure handling. Covers complexity of a tool that aggregates from two external services.

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 context: scoped packages accepted for 'package', and 'version' defaults to latest. This enriches the schema meaning for an agent.

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

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

The description clearly states it's a composite check for npm packages, aggregating data from deps.dev and bundlephobia. It uses a specific verb phrase ('should I add this npm package to my project check') and distinguishes from sibling tools by focusing on npm dependency scanning.

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

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

Explicitly says 'Use whenever an agent asks "is X safe / popular / small"...' and notes ecosystem limitation ('NPM ecosystem only in v1'). Provides alternative guidance for non-npm packages by mentioning deps.dev directly.

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

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

Annotations already note readOnly, openWorld, idempotent, non-destructive. Description adds truncation cap (200K chars), embedding model (BGE-base-en), cosine similarity over 500-char windows, and offset returns. Adds significant behavioral context beyond annotations.

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

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

Three sentences, no wasted words, front-loaded with key purpose and use case. Structure is clear and efficient.

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

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

No output schema, but description adequately explains return format (passages with offsets and similarity scores). Also covers pairing, caps, embedding details. Complete 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 coverage is 100%, so baseline 3. Description adds value by providing examples for 'text' and 'query', and specifying range/default for 'limit'. Meaningfully extends 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?

Description clearly states it performs semantic search inside a fetched record, with specific examples like SEC 10-K or article. It distinguishes from sibling tool 'ask_pipeworx_grounded' by mentioning pairing and use case.

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

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

Explicitly says when to use: when record is too big for prompt, saves context. Pairs with sibling tool. Implicitly advises against use for small records.

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

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

Adds good context about delivery channels, SMS cap, webhook secret, and auto-disable. However, annotation idempotentHint=true contradicts description which implies each call creates a new subscription (not idempotent). This is a significant inconsistency.

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

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

Well-structured with front-loaded purpose and return value. Each sentence adds value, but length is slightly above minimal; still efficient.

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

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

Covers purpose, return value, account requirement, types, delivery options, and constraints. Lacks mention of error conditions or how to use returned subscription id, but adequate for a creation tool with no output schema.

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

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

Schema coverage is 100%, but description adds rich examples and constraints for each type and delivery channel, such as specific item codes for sec_8k and SMS/day cap.

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 verb 'Create' and resource 'proactive monitoring subscription to a live-data event stream' and explicitly mentions 'Returns the new subscription id'. Differentiates from sibling tools like 'unsubscribe' 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?

Specifies account requirement (Pipeworx OAuth, no anonymous/BYO), and explains supported types with example parameters. Does not explicitly state when not to use or compare with alternatives like 'recent_alerts', but provides clear context for usage.

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

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

Annotations already declare readOnlyHint=true, idempotentHint=true, etc. Description adds context about returning category-bucketed example questions with tool shapes, drawn from live catalog, and optional topic filter.

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 slightly long but front-loaded with user-like queries and structured with categories and usage instructions. Each sentence adds value, though could be tightened.

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

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

Given the tool's role as an onboarding entry point with no output schema, the description fully explains what it returns (category-bucketed examples with tool+argument shapes) and when to use it.

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

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

Schema coverage is 100% with one optional parameter. Description explains the topic parameter's purpose, gives example values, and clarifies behavior when omitted (full spread).

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 the onboarding entry point, with specific verb+resource and distinguishes from sibling tools by being the first tool to use when learning about Pipeworx capabilities.

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 this FIRST when you do not yet know what Pipeworx can do for you' and provides context for when to use and what it returns, with alternative meta-tools hinted.

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 provide non-destructive and idempotent hints. Description adds crucial detail: row is deactivated not deleted, and historical events stay via recent_alerts. This goes beyond annotations and clarifies exact side effects.

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

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

Two sentences, front-loaded with action, followed by key behavioral context. No filler or redundant information. Efficient and clear.

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

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

For a simple 1-param tool with no output schema, the description covers cancellation, ownership, deactivation, and relates to recent_alerts. Fully complete for its complexity level.

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

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

Input schema already documents the single parameter 'id' with full description. The description does not add new parameter-level info beyond what schema provides. Baseline 3 is appropriate.

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

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

Description clearly states 'Cancel a subscription by id' – specific verb and resource. Distinguishes from sibling tools like subscribe and list_subscriptions. Also mentions ownership enforcement, further clarifying 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?

Describes ownership enforcement ('you can only cancel your own subscriptions') and explains behavioral nuance (deactivation not deletion with link to recent_alerts). Does not explicitly list when not to use or alternatives, but 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 declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, establishing safety. The description adds behavioral details about the return values (verdict types, structured form, citation, percent delta) and that it simplifies multiple calls. 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 well-structured with front-loaded key phrases. It includes examples, domain specification, and output details. While slightly verbose, every sentence contributes value. Could be slightly more concise but still effective.

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

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

Given that there is no output schema, the description fully covers expected outputs (verdict types, structured form, actual value with citation, percent delta). It also specifies data sources (SEC EDGAR + XBRL) and domain scope (US public companies). No gaps remain.

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

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

Schema coverage is 100%, and the schema's parameter description is adequate. The tool's description provides examples of claims but adds minimal extra meaning beyond the schema. Baseline score of 3 is appropriate.

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

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

The description clearly states the tool's purpose: natural-language claim verification against authoritative sources. It uses multiple intuitive phrases ('Is it true that…', 'fact check') and specifies the domain (company-financial claims for public US companies). This distinguishes it from sibling tools like bet_research or deep_research.

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

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

The description explicitly says 'Use whenever the agent needs to check whether something a user said is factually correct.' It also mentions it replaces multiple sequential calls, providing clear context for when to use. However, it does not explicitly state when not to use it or mention alternatives.

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