Exa

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds valuable behavioral context: it makes external API calls, describes cost implications (free vs BYO key), and details the return structure. No contradictions.

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

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

Two sentences, front-loaded with purpose, minimal waste. Every clause adds value. Structurally 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 fully explains the return format (per-model {score, confidence, signals, raw_response} + combined) and all parameters are covered. Complete for a non-nested, 4-parameter 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 each parameter described. The description adds extra context: default model, API key purpose, and context disambiguation. It goes beyond the schema but not drastically.

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 returns a visibility score per model. It distinguishes itself from sibling tools like 'scan_competitor_ai_presence' by focusing on scoring rather than general scanning, and from 'ask_pipeworx' by being a probe not a Q&A 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 states when to use: AI-marketing audits, pre-launch brand checks, competitive monitoring. It provides clear context: default model is free, Anthropic requires BYO key, and parameter usage is explained.

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

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

Annotations indicate readOnlyHint, openWorldHint, idempotentHint true, destructiveHint false. Description adds context about routing, argument filling, and returning structured answers with citation URIs. Does not mention rate limits or response times, but the behavioral traits are well-covered.

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 well-structured with bold headings and examples, but is somewhat lengthy. Front-loads key information and uses short sentences effectively.

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, many sources), the description covers usage scenarios, example queries, relationship to siblings, and return format (structured answer with citations). Complete enough for the 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?

Input schema has 100% description coverage with aliases listed. Description reinforces that the question parameter accepts natural language queries and gives examples. No additional meaning needed 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: routing questions to 4,552 tools across 1,160 sources and returning structured answers. It distinguishes from siblings like ask_pipeworx_grounded and deep_research, and provides concrete examples of usage.

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 prefer this tool over web search, when to use alternatives (ask_pipeworx_grounded for hallucination-resistant answers, deep_research for broad questions), and includes example queries. Provides clear guidance on when to step up to other tools.

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

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

Annotations already indicate read-only, open-world, idempotent, non-destructive. Description adds extra LLM call cost, return structure with evidence fields, and explicit refusal reasons, enhancing 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?

Description is dense but well-structured with front-loaded purpose and clear bullets for return values. Slightly verbose but every sentence adds value.

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

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

Given complexity (routing to many tools, refusal handling) and lack of output schema, the description thoroughly covers return structure, refusal reasons, cost, and compared to sibling, making it complete for reliable agent 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 covers 100% of parameters with aliases for 'question'. Description does not add new parameter semantics but explains usage context and return values indirectly. 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?

Clearly defines the tool as a hallucination-resistant answer mode for high-stakes reads. Distinguishes from sibling ask_pipeworx by explaining grounded extraction of answers with evidence. Specifies verb 'answer' and resource 'high-stakes reads'.

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 answers will be quoted, cited, or acted on, and in high-stakes domains. Advises preferring ask_pipeworx for casual lookups, providing clear 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 declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint=false. The description adds extensive behavioral details: market resolution, classification, fan-out to data packs, response shapes, safety mechanisms (low-confidence short-circuit, closed markets, wide spreads), cancellation rule parsing, and more. It far exceeds the annotation baseline.

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

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

The description is very long (multiple paragraphs) and detailed. While it is front-loaded with purpose and structured with sections, it could be more concise. It contains many details that could be in separate documentation. Still, it is well-organized 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?

Given the tool's complexity and lack of output schema, the description covers all necessary aspects: resolver contract, parent event extraction, news fields, safety checks, cancellation rules, and response shapes. It leaves no major gaps for the 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 coverage is 100% with descriptions for all parameters. The description adds value by explaining the market parameter with examples and clarifying depth and include_raw behavior. However, the schema already does the heavy lifting, so the description adds moderate extra meaning.

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

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

The description clearly states the tool's purpose: research a Polymarket bet by pulling Pipeworx data. It specifies input formats (slug, URL, question text) and gives usage examples. It distinguishes from sibling tools like polymarket_edges or polymarket_arbitrage by focusing on per-bet 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?

Description explicitly says when to use: 'Use for should I bet on X, what does the data say about Y, or is there edge in Z.' It also provides safety warnings about inspecting match confidence before trusting analysis. However, it does not explicitly compare to alternatives like polymarket_edges, but the context is clear enough.

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

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

Disclosures go well beyond annotations: explains data sources (SEC EDGAR/XBRL for companies, FAERS for drugs), handles off-calendar fiscal years, describes sorting behavior by primary metric, and mentions citation URIs. No contradiction with readOnlyHint, openWorldHint, idempotentHint, destructiveHint.

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 tightly packed with information using concise shorthand and examples. Front-loaded with typical user phrasing. Every sentence earns its place without 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?

Though there is no output schema, the description fully covers what is returned (paired data, sorted results, citation URIs) and the behavior for each entity type. Complete picture for an 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%, so baseline is 3. The description adds significant meaning: explains what each type returns (company financials vs. drug stats), clarifies values parameter format (tickers/CIKs for company, names for drug), and reiterates bounds (2-5 items). Adds 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 it performs side-by-side comparisons of 2-5 companies or drugs in a single parallel call. It gives concrete query examples, distinguishes between entity types, and implicitly differentiates from siblings like entity_profile (single entity) and search.

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

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

Explicitly instructs to ALWAYS PREFER this tool over sequential single-pack lookups when comparing entities. Provides clear context of when to use (comparing entities) and implies when not to (single entity lookups via entity_profile). Mentions efficiency gain (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?

Discloses behavioral traits beyond annotations: returns findings packet with evidence, confidence, source, citation, gaps; decomposes into facets with parallel execution; 15-60s wait; never invents data. Annotations already indicate read-only, idempotent, non-destructive; description adds rich 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?

Front-loaded with critical account requirement and alternatives. Structure is clear but slightly verbose; all sentences contribute to clarity.

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

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

Given no output schema, description thoroughly explains return format, edge cases (empty gaps for missing data), and best-use scenarios. Covers all aspects needed for proper 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%, but description adds value by explaining default for depth (standard=5) and that broad/multi-part questions are fine. Adds practical guidance beyond schema.

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

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

Clearly states it performs grounded multi-source research across 1160 structured data sources, distinguishes from siblings like ask_pipeworx for single lookups and news. Specific verb+resource+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 tells when to use this tool (broad/multi-part questions over structured data) and when not to (single lookup, breaking news), with named alternatives (ask_pipeworx). Also requires account, with fallback for non-signed-in 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?

Adds value beyond annotations: explains it returns top-N relevant tools with full schemas and curated examples, ready to call directly. No contradiction with readOnlyHint or other 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 slightly long but well-structured and front-loaded. Every sentence adds value, though minor redundancy in listing aliases could be trimmed.

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 fully explains return values (names, descriptions, full schemas with examples) and states it's ready to call. Complements the large set of sibling tools.

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 meaningful context: explains query accepts natural language, lists aliases, and provides examples, improving parameter understanding.

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

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

The description clearly states the tool finds tools by describing data or task, lists specific domains, and distinguishes itself from siblings as the tool for browsing/searching tools.

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

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

Explicitly says 'Call this FIRST when you have many tools available and want to see the option set', providing clear context for use, but lacks explicit 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 readOnly, openWorld, idempotent, and non-destructive. Description adds significant behavioral context: parallel call execution, fan-out across multiple sources, patent soft-fail due to USPTO sunset, and fallback mechanisms (GDELT→GNews). 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?

Info-dense but well-structured: starts with example queries, then usage guidance, then detailed fan-out and return fields. Each sentence adds value, though minor verbosity prevents a 5.

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 2 simple parameters and no output schema, description provides comprehensive return field details (cik, filings, fundamentals, etc.). Minor gaps: exact format or count of news items not specified, patent status noted as soft-fail. Still very complete for a complex tool.

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

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

Input schema has 100% coverage with clear descriptions for both parameters (type enum and value). Description reinforces that only ticker or CIK is accepted, not names, and points to resolve_entity. Adds useful context beyond schema.

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

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

Description clearly states the tool provides a full cross-source profile of US public companies, with example queries and listed return fields. It distinguishes itself from siblings like resolve_entity (for name resolution) and compare_entities, making its purpose unique.

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 to prefer this tool over chaining single-source lookups when a holistic view is needed. Also advises using resolve_entity first if only a name is available, 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 convey read-only, idempotent, open-world, and non-destructive behavior. The description adds minor context (neural/semantic matching and output fields) but does not significantly enhance transparency 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 extremely concise: two short sentences plus an example. It is front-loaded with the core purpose and includes a concrete usage example. Every word serves a purpose; 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?

For a tool with 3 parameters and no output schema, the description is fairly complete. It specifies inputs, return fields, and includes an example. Minor gaps: no mention of behavior when num_results exceeds max, or details on scoring. Still 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?

All three parameters have descriptions in the input schema (100% coverage). The description repeats 'url' and 'num_results' via an example but adds no additional semantic meaning beyond what the schema already provides. Baseline 3 is appropriate.

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

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

The description clearly states the tool's action: find pages semantically similar to a given URL. It specifies the method (neural/semantic matching) and the output fields (title, URL, relevance score, published date), leaving no ambiguity. It is distinct from sibling tools like 'search' and 'search_within'.

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 does not explicitly provide when to use or avoid this tool versus alternatives. While the purpose is clear, it lacks guidance on choosing over 'search' or 'find_similar' in specific scenarios. Usage is implied but not detailed.

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

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

Annotations already provide destructiveHint=true and idempotentHint=true. Description adds context about clearing sensitive data but doesn't detail behavior on missing key or deletion permanence.

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 purpose, then usage guidance. 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?

Covers purpose, usage, and sibling relationships. Missing behavior on non-existent key, but adequate for a simple deletion tool given annotations.

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 is adequate. Description does not add meaning beyond the schema.

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

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

The description clearly states 'Delete a previously stored memory by key' with a specific verb and resource, distinguishing it from siblings like remember and recall.

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

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

Explicitly advises when to use: stale context, task done, clear sensitive data. Mentions pairing with remember and recall, but does not explicitly exclude 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 declare readOnlyHint=true, idempotentHint=true, destructiveHint=false. Description adds behavioral details: fetches the page, extracts content, emits markdown. This goes beyond annotations, though it omits error handling or rate limits. 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?

Three sentences front-load the main purpose and output format. Every sentence adds value without redundancy. 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?

Despite no output schema, the description specifies the output as a single text blob in llms.txt markdown format. Use cases are explained. For a simple two-parameter tool, it is fully 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 both parameters well described. The description does not add new information about the parameters beyond what the schema already provides, so score is at baseline 3.

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

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

The description uses a specific verb 'Generate' and resource 'llms.txt file for any URL'. It clearly explains the tool extracts title/description/key links and outputs standard markdown, distinguishing it from sibling tools like ai_visibility_check or scan_competitor_ai_presence.

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

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

The description lists explicit use cases: getting a client's site indexed, drafting llms.txt for own project, auditing competitor. It provides context for when to use but does not explicitly mention when not to use or directly contrast with siblings, though the tool's purpose is unique.

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, so the safety profile is clear. The description adds that contents are 'clean, parsed' and provides an example, but does not elaborate on behavior beyond what annotations imply, such as error handling 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 two concise sentences plus an inline example. Every sentence adds value, with no redundant or extraneous 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?

For a simple read-only tool with no output schema, the description adequately covers purpose, usage context, and parameter semantics. It could mention the output format or what 'parsed' entails, but overall it is sufficiently complete given the tool's simplicity and annotation coverage.

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 for both parameters, so the schema already explains 'ids' and '_apiKey'. The description only provides an example usage, which adds marginal value over 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?

Description clearly states the verb 'Retrieve' and resource 'clean, parsed page contents' for one or more Exa result IDs or URLs. It distinguishes itself from search by specifying 'Use after search to read the full content of pages.' Sibling tools include 'search', so the purpose is distinct.

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 after search to read the full content of pages,' providing clear context for when to use this tool. However, it does not mention when not to use it or suggest alternatives among siblings, which keeps it from a 5.

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

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

Annotations already declare readOnlyHint and idempotentHint. Description adds return field list and parameter behavior but doesn't mention additional constraints like rate limits or authorization beyond 'caller's'.

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 efficient sentences, front-loaded with main purpose, minimal waste.

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

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

Given one optional parameter, no output schema, and strong annotations, the description fully covers what the agent needs to know for correct invocation.

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

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

Schema coverage is 100% and schema already describes include_inactive parameter. Description does not add new semantic meaning beyond the schema.

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

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

Clearly states 'List the caller's active subscriptions' with a specific verb and resource. Distinguishes from sibling tools like subscribe and unsubscribe.

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

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

Explicitly says 'Use this to review what you're monitoring before adding more or to find an id to cancel', 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?

The description reveals behavioral traits beyond annotations: rate-limited to 5 per identifier per day, free, and doesn't count against tool-call quota. No annotation contradiction exists.

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

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

The description is concise and well-structured: it starts with the core purpose, then provides usage scenarios, formatting advice, and limitations. Every sentence adds value without redundancy.

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

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

Given the tool's simplicity and lack of output schema, the description is complete. It covers all necessary details: what to submit, how to format, rate limits, and quota impact. 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 description adds value by defining the enum values for 'type' (bug, feature, etc.) and explaining the optional context fields. While the schema already has descriptions, the tool's description reinforces them with practical usage context.

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

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

The description clearly states the tool's purpose: to send feedback to the Pipeworx team about bugs, feature requests, data gaps, or praise. It provides specific use cases and distinguishes the tool from siblings by focusing on feedback submission rather than information retrieval or actions.

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

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

The description explicitly states when to use the tool for different feedback types (bug, feature, data_gap, praise) and provides best practices such as describing issues in terms of Pipeworx tools/packs and not pasting end-user prompts. It also mentions rate limits and quota details, offering complete 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, idempotent, non-destructive. Description adds valuable context: data source (CF analytics-engine), no PII, caching behavior (5min-1h). 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 front-loaded sentences with bullet list, no wasted words. Every sentence adds value: purpose, usage, behavioral traits.

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 simple tool (one optional param, no output schema), description covers return values, data source, privacy, caching, and usage. 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 covers 100% with enum and description. Description repeats the schema's window explanation but does not add new meaning beyond it. 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 returns top tools, packs, and call volume from Pipeworx trending data, distinguishing it from sibling tools like ask_pipeworx or discover_tools.

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

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

Explicitly lists three use cases (discovering hot data sources, confirming canonical tool, aligning use case with agents). Does not exclude alternative tools, but contexts are clear and actionable.

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

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

Annotations declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint. The description adds extensive behavioral context: internal checks (monotonicity, partition-sum, Jaccard similarity, placeholder filtering), response structure, fill check behavior, and trading advisories ('do not trade it' if realizable_edge_pp ≤ 0). 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 and well-structured with clear sections (mode selection, event details, topic details, filters, response, fill check). It is front-loaded and every sentence adds value, but it is somewhat verbose; could be slightly more concise while retaining completeness.

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, but the description fully explains the return structure: 'opportunities[] (gap_pp, suggested_trade, reasoning, monotonicity violation context), and in event mode partition_check...'. It covers all essential aspects: scanning modes, filters, fill check, and references custom sizing via polymarket_fill_risk.

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

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

Schema covers both parameters (event, topic) with descriptions. The description adds significant meaning: explains event mode with slug examples and market walking, topic mode with seed question examples and cross-event scanning, including the semantic anchor (Jaccard similarity ≥0.30) and partition filter logic.

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 from sibling tools like polymarket_fill_risk and polymarket_kalshi_spread by specifying its unique detection methods.

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

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

Explicit guidance is provided: 'Call with NO args for a trending_scan... pass `event` for the strongest per-event partition_check, or `topic` for a themed cross-event scan.' It recommends event mode for specific markets and explains when to use each mode, including a note on custom sizing referencing polymarket_fill_risk.

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

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

Annotations indicate read-only, idempotent, non-destructive. The description adds extensive behavioral details: caching (1h KV-level), edge calculation (net of slippage, Kelly fractions), diagnostics for empty segments, and caveats (Fed data unreliability). No contradiction with annotations.

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

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

The description is long (~600 words) but well-structured with sections (model families, knobs, response top-level). Every sentence adds value, but it is dense and could be slightly more concise without losing essential details. Front-loaded with 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 9 parameters, complex response structure, no output schema, the description compensates fully. It explains response segments, edge computation, diagnostics, caching, and filtering logic. All necessary context for correct invocation is present.

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 schema: explains defaults, practical usage ('Bump for very thin partitions'), and interactions (e.g., min_partition_leg_kelly for partition arbs not filtered by min_kelly). This helps the agent understand parameter impact.

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

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

The description clearly states the tool's purpose: 'Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price.' It is specific about the resource (Polymarket markets) and action (scan and return opportunities). The explanation of three response segments distinguishes it from siblings like polymarket_arbitrage.

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

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

Explicit guidance: 'Built for "what should I bet on today"' and 'agents discover opportunities without paging hundreds of markets.' It describes when to use and what to avoid (e.g., Fed candidates excluded, tradeable-edge knobs for filtering). No alternatives are named, 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 declare non-destructive, read-only, and idempotent behavior. The description adds significant behavioral detail: response structures (tracked, expired, snapshot_dates), field meanings (trend, decay_pp_per_day), and limits (60-day TTL, daily closes). 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 fairly detailed but organized: purpose, response breakdown, limits. Every sentence adds value, though slightly verbose. Could be tightened without losing clarity.

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

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

Despite lacking an output schema, the description thoroughly explains the return structure (tracked, expired, snapshot_dates with field details) and mentions limits. For a tool with 2 simple optional params, this is complete and actionable.

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 both parameters described. The description repeats the parameter names and defaults but does not add substantial new semantic information beyond what the schema already 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 provides 'edge persistence and decay telemetry' built from daily snapshots. It answers a specific question about edge age and trend, distinguishing itself from sibling 'polymarket_edges' which likely offers only current snapshots.

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

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

The description implies usage when assessing edge persistence versus freshness, using an example contrasting a fresh wide edge with a 3-week-old one. While it doesn't explicitly list alternatives or when not to use, the context of sibling tools makes the differentiation 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 (readOnlyHint, idempotentHint, etc.) are consistent with a read-only check. The description adds behavioral details: walks the order book ladder, returns verdict (clean/degraded/cannot_fill), and explains risk of partial fills, which 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 thorough and well-structured with clear sections, but is quite long. Every sentence adds value, but a slight trim could improve conciseness 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 complexity (two modes, no output schema), the description comprehensively explains return fields (top_of_book, vwap_fill_price, slippage_pp, shares_filled, max_fillable_usd, verdict, per-leg details, thin_legs, forced_directional_risk) and the risk of partial fills. Annotations and schema are fully complemented.

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 context: explains modes for market vs event, side defaults and auto behavior, size_usd interpretation for buys vs sells and basket mode (settlement notional). This exceeds what the schema provides.

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

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

The description clearly states the tool checks realizable vs theoretical edge against live CLOB order-book depth, with two modes (single-market and basket). It explicitly distinguishes from siblings like polymarket_arbitrage and polymarket_edges, specifying to use this tool before acting on their signals.

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 requires one of market or event, explains when to use each mode. Provides a specific condition (trades above ~$500) and warns about partial basket fills converting arbs into unhedged directional positions.

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

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

Annotations already declare readOnly and idempotent, but description adds extensive behavioral details: compatibility_warning conditions (non-equivalent bet shapes, unrelated events), temporal alignment field, skipped types counters, and explanations of why spreads may be meaningless. 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?

Description is fairly long but well-structured with clear sections (TWO MODES, RESPONSE, SAFETY FIELDS). Uses bold for emphasis and lists for readability. Every sentence adds necessary information for a complex tool, though slightly 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?

Given no output schema, the description comprehensively explains response fields (each venue's leg-by-leg prices, spread array, top_spreads_pp), safety fields (compatibility_warning, temporal_alignment, skipped counters), and failure modes. An agent can fully understand what to expect and how to interpret 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% (all params documented) so baseline 3. Description adds value by explaining that topic is a pre-mapped shortcut with a specific list, and that explicit params override topic. Also provides examples. Exceeds 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?

Description clearly states it computes cross-venue spread between Kalshi and Polymarket, distinguishing it from sibling tools like polymarket_arbitrage which focus on intra-venue arbitrage. Specifies two modes (topic shortcuts and explicit pairing) and explains the response fields, making the tool's purpose very clear.

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

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

Provides explicit guidance on when to use each mode (topic for common macros, explicit for custom pairings) and warns that pre-mapped topics often yield compatibility warnings, so they are not tradeable. Lacks direct comparison to sibling tools but sets clear expectations.

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. Description adds value by explaining scoping (per identifier) and pairing with remember/forget. 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?

Three sentences, front-loaded with purpose, no redundant information. 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?

For a simple retrieval tool with no output schema, description sufficiently explains return behavior (value vs. list), scoping, and relationship to sibling tools. 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 a single 'key' parameter described. Description adds real-world examples of what the key might represent (ticker, address, notes), 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?

Description clearly states the tool retrieves a saved value or lists all keys, distinguishing it from siblings (remember, forget) by naming them. Verb+resource is 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?

Description provides use cases (look up stored context like ticker, address, notes) and mentions scoping. Does not explicitly state when not to use, but context is clear given sibling tools.

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

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

Annotations declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds value by explaining the effect of mark_read:true (flags events as read so subsequent calls only show newer ones) and notes the feed consistency via a REST endpoint. 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?

Three sentences: first states purpose and return fields, second summarizes filtering, third addresses polling and alternative access. Each sentence earns its place with 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?

Given the tool has 5 optional parameters, no output schema, and no nested objects, the description covers purpose, return fields, behavioral traits (mark_read), and alternative access. It is sufficient for an agent to use the tool correctly.

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

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

Schema descriptions cover 100% of parameters. The description adds context by providing an example for type ('sec_8k') and clarifying the ISO timestamp format for 'since', enhancing 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?

The description clearly states 'Pull fired events from your subscription feed,' specifying the action, resource, and what it returns (source, citation_uri, raw event). It distinguishes from sibling tools like 'search' and 'recent_changes' by focusing on subscription feed alerts.

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 guidance on polling ('Polls work fine') and an alternative REST endpoint for scripts/dashboards, helping the agent decide when to use this tool versus the external API. It could be more explicit about when not to use it, 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, idempotentHint, and non-destructive behavior. The description adds significant behavioral context: fan-out to multiple sources, fallback from GDELT to GNews, soft-fail for USPTO due to API sunset, and return structure with grouped changes and citation URIs. No contradictions.

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

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

The description is front-loaded with example queries, then concisely explains sources, parameter details, and sibling differentiation. Every sentence adds value, and the structure is logical and scannable. No redundant or verbose phrasing.

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

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

Given the complexity (multiple sources, fallback logic, relative/absolute date formats, no output schema), the description is fully complete. It covers return structure, handling of API failures, and parameter nuances. The agent can invoke the tool correctly without additional 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?

Schema coverage is 100% (all three parameters documented). The description adds meaning beyond the schema: explains 'since' accepts ISO dates or relative shorthand, provides examples, recommends '30d' or '1m' for typical monitoring, and clarifies 'value' can be ticker or CIK. This additional guidance helps the agent use parameters correctly.

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

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

The description clearly states it provides a 'change feed for a company in the last N days/weeks/months in ONE parallel call' and lists the specific sources (SEC EDGAR, GDELT→GNews, USPTO). It includes example queries and explicitly distinguishes from the sibling tool 'entity_profile', making the purpose 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 gives explicit example queries and recommends when to use the alternative 'entity_profile' (for static profile regardless of window). However, it does not explicitly state when not to use this tool or provide exclusions, though the guidance is clear enough for an AI agent to decide.

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 idempotentHint, destructiveHint, readOnlyHint. Description adds session persistence (24h vs persistent), 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?

Four sentences, no fluff, front-loaded with purpose and examples, well-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?

Covers all needed aspects for a key-value store tool: usage, scope, persistence, pairings with recall/forget. No output schema needed.

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

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

Schema coverage 100% with clear key/value descriptions. Description adds example values but does not significantly extend 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?

Specific verb 'save' with resource 'data to reuse later', examples (ticker, address, preference), and distinguishes from recall/forget 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 ('discover something worth carrying forward') and pairs with recall/forget, plus scoping and persistence details.

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

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

Annotations already provide readOnlyHint, openWorldHint, idempotentHint, destructiveHint. The description adds that each call cascades through several lookup endpoints internally and replaces 2-3 manual lookups, giving insight into resource usage. 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 front-loaded with practical examples, followed by use case and type details. It is compact and efficient, with no unnecessary words. Slightly more could be trimmed, but overall well-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 specifies what is returned for each type (ticker, CIK, RxCUI, etc.) and includes citation URIs. It covers the essentials for an agent to understand outputs. However, it lacks details on error handling or disambiguation for multiple matches.

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 examples of acceptable values (e.g., 'AAPL', 'ozempic') and explains input format per type, enriching the schema's enum/string descriptions. This adds significant meaning beyond the schema.

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

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

The description clearly states the tool resolves a user-spoken name to a canonical identifier, with specific examples (ticker, CIK, RxCUI). It uses verb+resource ('resolve' + 'entity') and distinguishes from siblings by stating it is the first tool when you have a name but need an ID.

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.' It also lists supported entity types and their returns, providing clear guidance on when to use the tool. However, it does not explicitly state when not to use it or mention alternatives, though the context is clear given sibling tools.

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

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

Annotations (readOnlyHint, openWorldHint, idempotentHint, destructiveHint=false) already indicate safety and openness. Description adds behavioral details: probes each entity with ai_visibility_check, ranks by score, surfaces most/least recognized, and returns score/confidence/signal density. 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?

Description is 3 sentences, front-loaded with the core action, no redundancy. Every sentence adds value: function, example use case, output format. Perfect length for quick comprehension.

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 moderate complexity (4 params, no output schema), description explains how each parameter works, what the output looks like (ranked list), and the role of the first entity. Missing details: error handling, exact scoring mechanism, but sufficient for most use 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% (all parameters described). Description adds extra meaning: first entity is treated as 'subject' for narrative, context disambiguates common names, models list options. This compensates for lack of enums and nested objects.

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 action (compare, probe, rank, surface) and resource (AI visibility across entities). It distinguishes itself from sibling 'ai_visibility_check' by focusing on multiple entities side-by-side, and explicitly mentions competitive audits, making purpose 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?

Description provides a concrete use case ('competitive AI-marketing audits') and implies when to use it (when comparing multiple entities). It implicitly differentiates from 'ai_visibility_check' (single entity) and 'compare_entities' by specifying internal use of ai_visibility_check, but lacks explicit 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?

The description adds significant behavioral context beyond annotations: it fans out to two services, returns specific fields, lists potential failure modes (bundlephobia timeout 5-30s), and mentions sources_failed field. Annotations only provide readOnly/openWorld/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 front-loaded with the main purpose, then adds usage guidance and edge-case behavior. Every sentence contributes value, though it is somewhat lengthy. Could be slightly tighter but remains effective.

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

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

Given no output schema, the description thoroughly explains the return structure (summary block fields, per-advisory detail, links, alternative versions) and error handling (partial failures, sources_failed). Covers all key aspects of a complex 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%, so baseline is 3. The description does not add new parameter semantics beyond what the schema already provides; it only restates or slightly elaborates on package name format and version default behavior.

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 npm packages, combining deps.dev and bundlephobia to answer 'should I add this package' questions. It distinguishes itself from sibling tools by specifying the exact data sources and the question it answers.

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

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

The description explicitly tells when to use the tool ('when an agent asks is X safe/popular/small') and when not to use it ('NPM ecosystem only in v1; PyPI/Maven/Cargo/Go fall under deps.dev:version directly'). It also mentions graceful degradation on partial failures.

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

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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint. The description adds behavior about returning specific fields and optionally retrieving page text. It also notes the optional API key for higher limits, which is a behavioral trait. Not perfect, but adds meaningful 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?

The description is extremely concise: two sentences plus an example. It front-loads the key information (neural/semantic search) and immediately follows with return fields and optional feature. 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 no output schema, the description adequately explains return values (title, URL, etc.) and covers key parameters. It could mention pagination or error handling, but it is sufficient for a search tool. The sibling tool search_within is not referenced, but overall completeness is good.

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, so baseline is 3. The description adds value through a concrete example showing how to use query, num_results, and type, and it clarifies the meaning of the query parameter. 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 it performs neural/semantic web search, distinguishing it from traditional keyword search. It specifies the resource (web pages) and the action (search by meaning). The example further clarifies the purpose. While sibling tools like search_within exist, the description itself is 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 implies usage for meaning-based search and provides an example, but does not explicitly state when to use this tool versus alternatives like search_within or find_similar. No when-not guidelines are given.

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 operation, but description adds detailed behavioral traits: BGE-base-en embeddings, cosine similarity, 500-char overlapping windows, 200K char cap with truncation flag, and passage offsets for verification. This goes far 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 dense sentences front-loaded with purpose. All information is relevant, but the second sentence is quite long, containing multiple technical details. Still, no wasted words; slightly better structure (e.g., breaking into short bullet points) could improve readability.

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

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

Given no output schema, the description covers return format (passages, offsets, similarity scores) and mechanism (embeddings, windows, truncation). However, it lacks details like passage size or similarity score range. Overall fairly complete for a 3-param 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%, yet description adds value: for 'text' it specifies max ~200K chars, for 'query' gives concrete examples, for 'limit' states 1-20 default 5. It also explains the output structure (passages with offsets and scores), 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 clearly states it performs semantic search inside a fetched record, using specific verbs like 'search inside' and 'pass the text you already pulled'. It distinguishes itself from sibling tools by explaining it works on already-fetched text and pairs with ask_pipeworx_grounded.

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

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

Explicitly states when to use: 'when the record is too big to cram into the prompt'. Also describes the pairing with ask_pipeworx_grounded, providing a clear alternative workflow. This gives the agent strong guidance on context of use.

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

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

The description adds extensive behavioral context beyond annotations, including OAuth requirement, return value, delivery channel behaviors (SMS cap, webhook auto-disable, email validation), and that webhook secret is returned only once.

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

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

The description is well-structured with a clear purpose statement upfront, followed by prerequisites, supported types with examples, and delivery details. Every sentence is informative and no 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 the tool's complexity and lack of output schema, the description fully covers usage, prerequisites, parameter details, return value, and behavioral nuances, enabling correct 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?

Despite 100% schema coverage, the description enriches parameters with example values, explanations of type-specific params (e.g., sec_8k items codes), and additional constraints on delivery channels (phone verification, HMAC signing).

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

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

The description clearly states the tool creates a proactive monitoring subscription to a live-data event stream and returns the new subscription ID. It distinguishes from sibling tools like list_subscriptions and unsubscribe by focusing on creation.

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

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

It specifies the requirement for a Pipeworx OAuth account and details delivery channel constraints. While it doesn't explicitly say when not to use, the context implies it's for creating, not managing, subscriptions.

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

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

Annotations already provide readOnlyHint, openWorldHint, idempotentHint, and destructiveHint. The description adds valuable behavioral context: it returns category-bucketed example questions with exact tool shapes from a live catalog, and it is the first tool to use for onboarding.

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

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

The description is front-loaded with key phrases and provides comprehensive details. Although somewhat lengthy, every sentence adds value. Minor reduction could improve conciseness.

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 return structure (category-bucketed examples with tool+argument shapes). Annotations cover safety and idempotency. The description is complete for onboarding purposes.

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

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

Schema coverage is 100%, and the description adds meaning beyond the schema by explaining the topic parameter values (e.g., 'finance', 'pharma') and the effect of omitting it. It also clarifies the output nature (example questions with tool calls).

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 an onboarding entry point, specifying the verb 'ask' and resource 'Pipeworx'. It distinguishes from siblings by focusing on getting started and learning capabilities, listing example questions and categories.

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 to use this tool 'when you do not yet know what Pipeworx can do for you, or to learn how to call the meta-tools'. It also explains when to omit or pass the topic argument. While it doesn't explicitly exclude alternatives, the context is sufficient.

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

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

Beyond annotations (destructiveHint=false, idempotentHint=true), the description adds useful behavior: ownership enforcement, soft deactivation (row not deleted), and that historical events remain available. No contradiction with annotations.

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

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

Two concise sentences with no redundancy. The key information is front-loaded: action, resource, and key constraints.

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 one-parameter tool with no output schema, the description covers purpose, ownership, mutation behavior, and data persistence. Complete given 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?

The only parameter 'id' is already described in the input schema as 'Subscription id (uuid) returned by subscribe.' The description adds no extra meaning beyond the schema. With 100% schema coverage, baseline score 3.

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

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

The description clearly states the verb 'Cancel a subscription by id', specifying the action and resource. It differentiates from sibling tools like 'subscribe' and 'list_subscriptions' by focusing on cancellation.

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

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

The description provides context on when to use the tool (to cancel a subscription) and includes ownership enforcement details. It does not explicitly state when not to use or list alternatives, but the usage 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, openWorldHint, idempotentHint. Description adds behavioral context: returns verdict, structured form, actual value with citation, percent delta, and that it replaces multiple calls. No contradictions.

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

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

Description is front-loaded with trigger phrases and clear purpose. It is slightly verbose with multiple examples but efficient overall, with 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?

Given one parameter, no output schema, and annotations covering safety, the description adequately explains input, domain, and output format. It is complete for the tool's simplicity.

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

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

Schema coverage is 100% for single parameter 'claim'. Description adds meaning by explaining it is a natural-language factual claim with concrete examples, going beyond the schema description.

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

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

The description clearly states the tool verifies natural-language claims against authoritative sources, specifically company-financial claims for public US companies. It distinguishes from siblings by noting it replaces 4-6 sequential calls.

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

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

Explicitly says when to use: whenever checking factual correctness of a claim, with example trigger phrases. However, it does not explicitly list when not to use, though the domain limitation (company-financial) is implied.

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