Reactome

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

The description aligns with annotations (readOnlyHint, idempotentHint, destructiveHint false). It adds value by explaining the default free model, the billing implication for Anthropic calls (BYO key, direct payment), and the return structure (per-model details + combined view). No contradictions.

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

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

The description is three sentences with no fluff. The first sentence states the core purpose and output, the second adds model specifics and billing, the third lists use cases. Every sentence is actionable and necessary.

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 adequately describes the return format (per-model score, confidence, signals, raw_response + combined). It covers all parameters, gives usage context, and addresses billing. For a tool with 4 parameters and clear annotations, this is complete.

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

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

Schema coverage is 100%, so baseline is 3. The description adds meaningful context beyond the schema: it gives examples for 'entity' and 'context', specifies supported model values for 'models', and explains that _apiKey is passed directly to Anthropic. This extra guidance merits a 4.

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

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

The description clearly states the tool probes LLMs for knowledge about an entity and scores visibility (0-100) per model. It specifies the verb 'probe', the resource 'LLMs', and the output type. This distinguishes it from sibling tools like 'scan_competitor_ai_presence' which may focus on broader competitive analysis.

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

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

The description provides explicit usage contexts: 'AI-marketing audits, pre-launch brand checks, competitive monitoring'. It also explains when to use the optional _apiKey parameter and default model. However, it does not explicitly state when not to use this tool or contrast with very similar siblings.

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

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

Annotations already declare readOnlyHint, idempotentHint, etc. The description adds valuable context: routes to many tools, fills arguments, returns structured answers with citation URIs. No contradictions.

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

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

Single paragraph with key information front-loaded (preference over web search) and examples at the end. Efficient but could be slightly more concise. No wasted sentences.

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

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

Given the simple parameter and no output schema, the description adequately covers what the tool does, when to use it, and what to expect (structured answers with citations).

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

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

Schema has 100% coverage and describes the single parameter well. The description reinforces that the question is in natural language but adds no new semantic detail beyond examples. Baseline score of 3 is appropriate.

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

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

The description explicitly states the tool answers factual questions using authoritative structured data, listing specific domains (SEC, FDA, FRED, etc.) and contrasting with web search. It provides a clear verb ('ask') and resource ('Pipeworx').

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

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

Clearly indicates when to use ('prefer over web search') and gives concrete examples of user queries. However, it does not explicitly mention when not to use or compare with sibling tools like 'search' or 'deep_research'.

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

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

Describes internal routing, extraction logic, return structure including refusal reasons, complementing annotations (readOnlyHint, idempotentHint) with no contradictions.

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

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

Concise, front-loaded with key purpose, structured for quick scanning, 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?

Comprehensive for a tool with no output schema but rich annotations; explains behavior, return, refusal reasons, and usage guidance fully.

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

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

Schema description coverage is 100%, so description adds minimal value beyond listing aliases; baseline 3 is appropriate.

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

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

Description clearly defines the tool as a hallucination-resistant answer mode for high-stakes reads, distinguishing it from ask_pipeworx by specifying its grounded extraction process.

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 (high-stakes, quoted/cited answers) and when not (prefer ask_pipeworx for casual lookups), with clear context.

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

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

The description extensively details behavioral traits beyond annotations: low-confidence resolution handling, closed market detection, wide-spread warnings, resolution-rule risk extraction, and safety mechanisms. Annotations are readOnlyHint, openWorldHint, idempotentHint, destructiveHint=false; the description adds critical context without contradiction.

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

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

The description is long but dense with valuable information, front-loaded with the main purpose and followed by examples, classifiers, fan-out examples, response shapes, and safety notes. While slightly verbose, each sentence adds value; minor structuring improvements could be made.

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

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

Given the tool's complexity (3 parameters, no output schema), the description covers inputs, outputs, edge cases, safety, resolution rules, and response shapes comprehensively. It leaves minimal gaps for an agent to misunderstand.

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 meaningful context for each parameter: market input examples, depth explanation, and include_raw with size implications. This enriches the schema definitions.

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

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

The description states clearly that the tool researches a Polymarket bet by pulling Pipeworx data, and it distinguishes itself from sibling tools like polymarket_edges and polymarket_arbitrage by offering a full research call. It includes specific examples of use cases.

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

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

The description explicitly provides use cases like 'should I bet on X', 'what does the data say about Y', or 'is there edge in Z'. It explains input types and behavior but does not explicitly state when not to use this tool versus alternatives, though the context is clear.

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

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

Beyond annotations (readOnly, openWorld, idempotent, non-destructive), the description discloses exact data sources (SEC EDGAR/XBRL for companies, FAERS/FDA/trials for drugs) and handling of off-calendar fiscal years. No contradictions with annotations.

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

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

The description is a single, dense paragraph front-loaded with common query patterns. Every sentence contributes essential information without waste. It efficiently explains behavior, use cases, and the advantage over alternatives.

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 (2 parameters, type-driven behavior) and sufficient annotations, the description covers data sources, return format (paired data + citation URIs), and its advantage. Minor gap: no mention of pagination or limits (but maxItems=5 limits input).

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 value by elaborating on what data each type retrieves (e.g., 'pulls LATEST 10-K revenue...' for company, 'FAERS adverse-event counts...' for drug), which goes beyond the schema's enum labels.

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

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

The description clearly states the tool does side-by-side comparison of 2-5 entities (companies or drugs) in one parallel call. It distinguishes from siblings by explicitly preferring this over sequential single-pack lookups.

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

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

The description provides explicit guidance: 'ALWAYS PREFER over sequential single-pack lookups when comparing entities.' It also lists example queries like 'Compare X and Y' and explains entity types. However, it does not specify when to avoid using the tool (e.g., for single entity 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 indicate readOnlyHint=true and idempotentHint=true. The description adds valuable behavioral context: parallel processing, extraction of verbatim evidence, confidence scores, sources, timestamps, stable citations, and explicit gap reporting for unanswered facets. No contradictions with annotations.

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

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

The description is detailed yet concise, front-loading the main purpose and key capabilities. Every sentence adds value, with clear structure: what it does, how it works, output format, usage contexts, prerequisites. No wasted words.

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

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

Despite no output schema, the description fully explains the return value (structured findings packet with citations, gaps, etc.). Given the tool's complexity, this provides sufficient context for an AI agent to understand and invoke the tool correctly.

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

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

Schema coverage is 100% but description adds meaning: explains the depth enum values explicitly (quick=3, standard=5, thorough=8) and notes paid plan requirement for thorough. For the question parameter, it clarifies that broad/multi-part questions are accepted, which is core to the tool's purpose.

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 primary function: 'Grounded multi-source research in ONE call'. It explains the decomposition and parallel execution across thousands of tools and sources. It also distinguishes from sibling tool ask_pipeworx for single lookups.

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

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

Explicit usage guidance is provided: 'Use for broad or multi-part questions' and 'use ask_pipeworx for single lookups'. Prerequisites (Pipeworx account, paid plan for thorough) are clearly stated.

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

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint. The description adds that results include full schemas and are ready to call, which is useful context beyond annotations.

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

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

Three sentences; front-loaded with core purpose. The list of domains is a bit lengthy but useful. Could be slightly more compact without losing value.

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

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

Covers return format (top-N, with schemas, ready to call). No output schema, but enough for a discovery tool. Missing mention of pagination or error handling, but not critical.

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

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

Schema coverage is 100%, so baseline 3. The description adds examples and explains aliases, providing extra clarity beyond schema descriptions.

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

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

The description clearly states the tool finds tools by describing data or task, lists many example domains, and distinguishes it as the discovery gateway among many action-oriented 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 says 'Use when you need to browse, search, look up, or discover what tools exist' and instructs 'Call this FIRST when you have many tools available.'

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

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

Annotations already indicate read-only, idempotent, open-world behavior. The description adds valuable context: parallel call, sources fanned across, specific returned fields, and the USPTO sunset soft-fail. This provides operational details beyond annotations, though some error handling details are implicit.

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

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

The description is front-loaded with the core purpose and example queries, then elaborates on details. It is well-structured but slightly lengthy due to the example list. Nonetheless, every sentence adds value, and the structure aids 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?

The description is comprehensive for a tool with no output schema: it lists all returned fields, notes the USPTO soft-fail, specifies input constraints (ticker/CIK), and mentions it's for US public companies. It could explicitly mention authentication or rate limits, but the annotations cover read-only safety, making it largely complete.

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

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

Schema descriptions for both parameters are already detailed (type enum, value format). The description adds usage examples and reiterates the name constraint, but does not introduce new parameter-specific semantics beyond what the schema provides. Baseline 3 is appropriate given 100% schema coverage.

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

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

The description clearly states the tool provides a 'full cross-source profile of a US public company in ONE parallel call.' It uses specific verbs ('fan out across', 'returns') and distinguishes from chaining multiple lookups, making the purpose unmistakable.

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

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

The description explicitly says 'ALWAYS PREFER over chaining single-pack SEC/XBRL/news lookups when the user asks for a holistic view.' It also advises to 'use resolve_entity first if you only have a name,' providing clear when-to-use and when-not-to-use guidance with an alternative tool.

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

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

Annotations already indicate destructiveHint=true and idempotentHint=true; description adds context about clearing sensitive data but doesn't reveal significant new behavioral traits beyond annotations.

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

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

Two sentences, no fluff, front-loaded with action, and complete.

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

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

For a simple tool with one parameter and good annotations, the description is adequate, but lacks mention of return behavior or error cases; still sufficient for agent decision.

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

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

Schema coverage is 100% with a clear description for the single parameter 'key'. The description adds no additional parameter details 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?

States exact action ('Delete a previously stored memory by key'), verb+resource, and distinguishes from siblings ('Pair with 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?

Provides clear when-to-use scenarios (stale context, task done, clear sensitive data) and mentions pairing with 'remember' and 'recall', but lacks explicit when-not-to-use.

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

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

Adds details beyond annotations: fetches page, extracts title/description/links, emits markdown format. No contradiction; safely describes read-only, idempotent behavior.

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

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

Two concise sentences plus bullet list of use cases. Front-loaded with the main action, 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?

Covers main aspects for a simple 2-param tool without output schema. Mentions output format as single text blob, though could mention error handling briefly.

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

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

Adds value over schema by specifying default (25) and max (50) for max_links. Schema coverage is 100% but description enriches 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?

Clearly states the verb (generate), resource (llms.txt file), and scope (for any URL). The description differentiates from sibling tools by specifying the standard format and AI crawler use case.

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

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

Provides explicit use cases (client indexing, own project, competitor auditing) but does not mention when not to use or compare with alternatives.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint false. The description adds that the tool returns specific fields and is scoped to the caller. This adds some context but is not extensive.

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

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

Two concise sentences, no wasted words. The verb 'List' is front-loaded. Structure is optimal.

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

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

Given the simplicity of the tool and full schema coverage, the description clearly explains purpose and return fields. It could mention pagination or limitations, but overall it is adequate.

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

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

Schema has 100% coverage for the single parameter include_inactive. The description does not elaborate on the parameter, but the schema description is sufficient. Baseline 3 is appropriate.

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

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

Description starts with 'List the caller's active subscriptions,' clearly specifying the verb and resource. It 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?

Provides explicit usage context: 'Use this to review what you're monitoring before adding more or to find an id to cancel.' It implies when to use, but could mention when not to use.

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

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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false, so the description does not need to repeat safety traits. However, the description adds no behavioral context beyond the basic function (e.g., rate limits, authorization, or edge cases like missing orthologs).

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 concise at 4 words, but it effectively communicates the core purpose. Every word earns its place. It is front-loaded and avoids extraneous detail, though it could be slightly expanded for 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 the tool's simplicity (2 required params, annotations cover behavior, and an output schema exists), the description is complete enough to inform an agent of its purpose. No critical gaps are present, though it could mention that it retrieves orthologous events specifically from Reactome to align with the schema's example.

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

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

Schema coverage is 100%, so the input schema already describes both parameters ('id' and 'species') with clear descriptions. The description does not add any additional meaning or constraints beyond what the schema provides, meeting the baseline expectation.

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 'Orthologous pathways/reactions in another species' clearly states the tool's function: finding equivalent events across species. It is specific (verb: lookup, resource: orthologous events) and distinguishes from sibling tools like 'pathway' or 'pathways_for_entity' which focus on a single species.

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 a user wants to find orthologous events in another species, but it does not provide explicit guidance on when to use this tool versus alternatives like 'pathway' or 'search_within'. No when-not-to-use conditions are mentioned.

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 no behavioral context beyond a restatement of the name. It does not contradict annotations, but adds no value.

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

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

The description is a single short sentence, making it concise. However, it sacrifices clarity and informativeness. It could be expanded slightly to improve understanding without becoming 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 the tool has one parameter and an output schema, the description should explain what participants are and what the output contains. It fails to do so, leaving the agent without enough context to use the tool correctly alongside 20+ 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 description coverage is 0% for the single parameter 'id'. The description implies 'id' is a pathway ID ('participants of a pathway'), but does not confirm or explain format, examples, or constraints. Minimal clarification.

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 is vague: 'Entity participants of a pathway.' It lacks a verb indicating the action (e.g., list, get, retrieve) and does not clearly distinguish from sibling tools like 'entity_profile' or 'pathway'. The meaning of 'Entity participants' is ambiguous.

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

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

No guidance on when to use this tool versus alternatives. No mention of context, prerequisites, or exclusion criteria. Sibling tools cover similar ground but no differentiation is provided.

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

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint. The description adds minimal behavioral context (the id format example) but does not elaborate on what 'Full pathway record' entails.

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 one concise sentence, front-loaded with the action and resource, with zero wasted words.

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

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

Given the tool's simplicity (1 required parameter, read-only, output schema exists), the description is complete: it explains the input and implies the output (full record, supplemented by the output schema).

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

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

With 0% schema description coverage, the description compensates by explaining the 'id' parameter expects a stable identifier (e.g., R-HSA-68886), adding context beyond the schema's type-only definition.

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

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

The description clearly states the tool returns a full pathway record by stable id, with an example. It is specific but does not explicitly differentiate from sibling tools like 'pathways_for_entity'.

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

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

The description provides no guidance on when to use this tool versus alternatives, nor any exclusions or context.

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

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

Annotations already indicate read-only, open-world, idempotent, and non-destructive behavior. The description adds minimal additional behavioral context beyond the lookup mechanism, but does not contradict annotations.

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

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

The description is one clear, concise sentence that front-loads the purpose. It could be slightly more active ('Retrieve pathways...') but is efficient and uncluttered.

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

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

Given the presence of an output schema and full schema coverage, the description is adequate for a simple lookup tool. It does not address edge cases like missing entities, but the annotations and schema cover common needs.

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

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

Schema description coverage is 100%, so the input schema already provides full parameter meaning. The description does not add any extra context about parameter usage or semantics beyond what is 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 retrieves pathways containing an entity using an external resource ID, with an example. However, it does not explicitly differentiate from sibling tools like 'pathway' (singular) or 'participants', though the context implies distinction.

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

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

No guidance on when to use this tool instead of alternatives such as 'pathway' or 'participants'. The description only states what it does, not when it is appropriate or when to avoid it.

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

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

Discloses non-obvious behaviors: signals affect roadmap, team reads digests daily, rate-limited, free usage. Annotations are false for readOnly and destructive, which aligns with the description's intent.

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

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

Concise, front-loaded with purpose and use cases. Every sentence adds value—no redundancy. Well-structured for quick understanding.

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

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

Despite no output schema, description covers feedback lifecycle (team reads, impacts roadmap), rate limits, and quota exemption. Missing return value details are not critical for this feedback tool.

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

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

Schema covers all parameters with descriptions (100% coverage). Description adds value by reinforcing the format (describe in terms of tools/packs, not end-user prompts) and limits (2000 chars).

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 is for sending feedback to the Pipeworx team, with specific use cases (bug, feature, data_gap, praise). It distinguishes itself from sibling tools by being the sole feedback channel.

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

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

Explicitly explains when to use each feedback type, what not to do (avoid pasting end-user prompts), and provides rate limits (5 per identifier per day) and cost information (free, no quota impact).

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

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

Beyond annotations (readOnly, idempotent, openWorld), the description adds valuable behavioral details: caching (5min-1h), no PII, aggregated counts from CF analytics. This helps the agent understand the tool's non-safety implications.

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 efficient: front-loaded with purpose, followed by bullet-style use cases, then technical notes. Every sentence adds value, no fluff.

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

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

For a simple read-only tool with 1 parameter and annotations, the description covers return contents (tools, packs, volume), source, and caching. Lacks exact output format but given no output schema, this is sufficient. Nearly complete.

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

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

Schema has 100% coverage with a description already explaining the enum values. The tool description does not add new parameter semantics; it only implicitly references the window. Baseline 3 is appropriate since schema does the heavy lifting.

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

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

The description clearly states the tool returns top tools, packs, and call volume from other AI agents, with a specific verb 'returns' and distinct resource 'trending data from Pipeworx'. It differentiates from siblings like 'discover_tools' by focusing on real-time aggregate usage by other agents.

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

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

The description explicitly lists three use cases: discovering hot data sources, confirming canonical tool choice, and checking use case alignment. It does not explicitly exclude scenarios or name alternative tools, but provides clear context for when to use the tool.

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

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

Annotations declare read-only, open-world, idempotent. Description adds detailed behavior: monotonicity checks, partition checks, fill checks against CLOB depth, semantic anchor, partition filter. No contradiction; adds crucial context beyond annotations.

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

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

Description is verbose but every sentence is informative. Front-loaded with requirement. Could be slightly more structured (e.g., separate mode sections), but overall efficient for the complexity.

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

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

No output schema, but description thoroughly details return fields for both modes, including fill check conditions. Also covers failure modes (no args, low similarity, placeholders). Very complete given tool complexity.

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

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

Schema covers both parameters with descriptions. Description adds examples, explains mode differentiation, and notes that no args cause failure. Schema coverage is 100%, and description adds significant value beyond the schema.

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

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

Description clearly states the tool finds arbitrage opportunities on Polymarket via monotonicity violations and partition-sum checks. It distinguishes two modes (event and topic) and differentiates from siblings like polymarket_edges and polymarket_fill_risk.

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 `event` or `topic`, warns that no args fails, recommends when to use each mode, and explains when not to trade (realizable_edge_pp ≤ 0). References sibling `polymarket_fill_risk` for custom sizing.

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

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

Beyond annotations (readOnly, idempotent, non-destructive), the description discloses extensive behavioral traits: caching for 1h, detailed model families, tradeable-edge knobs, and diagnostic output. No contradictions with annotations.

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

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

The description is front-loaded with purpose and well-structured but very long and dense. It could be more concise with better formatting, though 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?

For a tool without output schema, the description fully compensates by detailing response structure (by_segment, diagnostics), edge cases (Fed bets, category counts), and filter explanations, making it complete for agent invocation.

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

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

All 9 parameters are already described in the input schema (100% coverage). The description adds context on how knobs like min_liquidity and max_spread_pp affect outcome, and explains internal logic beyond schema, providing 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?

Purpose is clearly stated: 'Scan top Polymarket markets and return opportunities where Pipeworx data disagrees with market price.' It specifies the verb (scan, return), resource (Polymarket markets), and distinguishes from siblings like polymarket_arbitrage by detailing unique model families and segments.

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 built for 'what should I bet on today'—a clear use case. However, it lacks explicit when-not-to-use guidance or alternatives among siblings, though the context is well implied.

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, which already inform the agent of safe, non-destructive behavior. The description adds valuable context: it reads daily snapshots (not intraday), requires 60-day TTL, and explains limits like history depth and decay computation. 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 dense and front-loaded with purpose, but it is verbose. It includes detailed response format inline (RESPONSE: ...) which, while informative, could be more concise. Some redundancy exists (e.g., explaining decay computation twice). Still well-structured but not optimally concise.

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

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

With no output schema, the description fully details the response structure: tracked[], expired[], snapshot_dates[]. It explains each field, including trend classification, decay rate, lifespan, and data gaps. It also covers history depth and decay limitations. This is exceptionally 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 2 parameters with 100% coverage and clear descriptions (days with default/clamp, window with default). The description reiterates these defaults and adds max=30 for days. Since schema coverage is high, the description adds marginal value beyond schema, resulting in a baseline score of 3.

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

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

The description clearly states the tool's purpose: edge persistence and decay telemetry from daily snapshots. It answers specific questions about edge age and decay, and distinguishes between fresh and old edges. The verb is implied but the resource (edge time-series) is specific. Compared to siblings like polymarket_edges, this one focuses on historical tracking.

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

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

The description explains when to use the tool: to understand edge history and decay. It contrasts fresh vs old edges, providing context for usage. However, it does not explicitly state when not to use it or name alternatives, though the sibling tools provide context. The guidance is clear but lacks explicit exclusions.

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

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

Annotations already indicate readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description vastly expands on behavior: it walks the order book ladder, returns specific fill metrics (top_of_book, vwap_fill_price, slippage_pp, etc.), and warns about forced directional risk and thin legs. This is additional rich 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 long but well-structured with capitalized mode headers and clear sections. It is front-loaded with essential information and avoids fluff. Every sentence serves a purpose, though some redundancy exists (e.g., repeating 'single-market' and 'basket' definitions). Minor verbosity prevents a perfect score.

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

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

Given the complexity (two operation modes, many return fields, no output schema), the description is remarkably complete. It lists all return fields, explains the verdict values, and describes risks and edge cases. No gaps are apparent.

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

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

Schema description coverage is 100%, so the description adds marginal value. However, it does clarify parameter behavior in each mode (e.g., size_usd meaning for single-market vs basket, side defaults). This contextual enrichment justifies a score above baseline 3.

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

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

The description clearly states it performs a realizable-vs-theoretical edge check against live CLOB order-book depth, with two distinct modes (single-market and basket). It explicitly contrasts with sibling tools like polymarket_arbitrage and polymarket_edges by prescribing when to use this tool before acting on those 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?

The description provides explicit when-to-use guidance: before any polymarket_arbitrage SELL/BUY-EVERY-LEG signal or any polymarket_edges trade above ~$500. It also explains the consequences of not using it (theoretical overround uncapturable, partial baskets converting arb to directional position), which is highly informative.

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

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

The description goes well beyond the annotations (readOnlyHint, idempotentHint, etc.) by detailing the behavior: auto-fetching events, response structure with leg-by-leg prices and spreads, and safety fields like compatibility_warning, temporal_alignment, and skipped_cross counters. It explains conditions when the tool outputs no useful data, enhancing transparency.

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

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

The description is lengthy but well-structured with clear sections (TWO MODES, RESPONSE, SAFETY FIELDS). It is front-loaded with the core purpose in the first sentence. While detailed, every sentence adds necessary context; however, slight tightening 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 the complexity of comparing two venues and the absence of an output schema, the description thoroughly covers the response format, safety fields, and common warnings. It explains potential pitfalls (non-equivalent bet shapes, misaligned temporal periods) and what the counters mean, making the tool's behavior clear.

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

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

The schema already describes all three parameters with examples and descriptions (100% coverage). The tool's description adds value by explaining the dual-mode logic and how explicit parameters override topic-mapped sides, providing deeper semantic understanding beyond the schema.

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

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

The description clearly states the tool computes the cross-venue spread between Kalshi and Polymarket for the same resolving question. It specifies two modes (topic shortcuts and explicit tickers), which distinguishes it from sibling tools like polymarket_arbitrage that likely focus on intra-venue arbitrage.

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

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

The description explicitly describes when to use the tool (to compare prices across venues) and the two modes of operation. It provides warnings via safety fields to indicate when spreads are not meaningful, which implicitly guides when not to rely on results. However, it could more directly state alternatives for when cross-venue comparison is not appropriate.

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 and idempotent behavior. Description adds scoping details (anonymous IP, BYO key hash, account ID) and pairing with remember/forget, providing extra context beyond annotations.

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

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

Two sentences plus a brief usage note, front-loaded with the core action. No redundancy or wasted words.

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

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

For a simple read-only tool with one optional parameter, the description covers the use case, scoping, and relationship to siblings. No output schema needed as return values are implied.

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?

Parameter 'key' is fully described in the schema (100% coverage). Description reinforces the schema but does not add new semantic meaning beyond what's already in the schema.

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

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

Description clearly states the tool retrieves a saved value or lists keys, with specific verb-resource pairs ('retrieve', 'list') and distinguishes itself from sibling tools like 'remember' and 'forget'.

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

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

Description explains when to use the tool (look up context stored earlier) and mentions scoping, but does not explicitly state when not to use or provide alternatives.

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

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

Description contradicts annotations: it states that setting mark_read:true flags events as read (a write operation), yet annotations declare readOnlyHint:true, meaning no state modification. This contradiction forces a score of 1.

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

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

Three sentences: purpose and data, filter examples, side effect and alternative access. No wasted words, efficient and well-organized.

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

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

Given 5 optional parameters, no output schema, and rich annotations, the description adequately covers purpose, data shape, filtering, side effect, and alternative access. No gaps for an agent to use correctly.

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

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

Schema coverage is 100%, so bar is baseline 3. Description adds example for 'type' and explains 'since' as ISO timestamp, but does not mention 'limit' parameter. Adds value on mark_read side effect, but not enough to exceed baseline.

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

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

The description clearly states the tool pulls fired events from the subscription feed and returns recent alerts with source, citation_uri, and raw payload. It effectively distinguishes itself from siblings like 'recent_changes' by specifying the feed context.

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

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

Provides clear context on filtering by type and since, and explains the effect of mark_read. Offers alternative access via URL. Lacks explicit when-not-to-use or direct sibling comparisons, but is still helpful.

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

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

Annotations already declare readOnlyHint, idempotentHint, and non-destructive. The description adds significant behavioral context: fans out to SEC EDGAR, GDELT/GNews fallback, USPTO with soft-fail note, and describes return structure (changes[], total_changes, citation URIs). This goes well 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 relatively long but each sentence adds value. It is front-loaded with example queries, then explains fan-out, parameters, return format, and sibling reference. It is well-structured, though slightly verbose due to the extended examples.

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 data sources, fallback, soft-fail), the description covers the main behaviors and return structure. No output schema exists, so description explains the return format. It lacks details on rate limits or pagination, but is complete for a single-call tool.

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

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

Schema description coverage is 100%. The description adds meaning: for since, it explains ISO date or relative shorthand with examples ('7d', '30d'); for value, says ticker or zero-padded CIK; for type, notes only 'company' supported. This enriches 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 provides a change feed for a company in the last N days/weeks/months, with example queries like 'What's new with X'. It distinguishes itself from sibling tool entity_profile, which is for static profile regardless of window. The verb 'change feed' and resource 'company' are specific.

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

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

The description explicitly tells when to use entity_profile instead ('when you want the static profile regardless of window'). It also explains the tool fans out to multiple sources in one parallel call, implying efficiency. However, it does not explicitly state when not to use this tool or list alternatives beyond entity_profile.

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 significant behavioral context beyond annotations: scoped by identifier, persistent for authenticated users, 24-hour retention for anonymous sessions. 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?

Four sentences, front-loaded with core purpose, no unnecessary words. Every sentence adds value.

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

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

For a simple two-parameter tool with no output schema, the description fully covers usage, scoping, and retention, making it complete for an agent.

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

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

Schema already covers both parameters (key and value) with descriptions. The description adds naming conventions and value types, enhancing semantics without redundancy.

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 ('Save') and resource ('data the agent will need to reuse later'), and clearly distinguishes from sibling tools like 'recall' and 'forget'.

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

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

Explicitly states when to use ('when you discover something worth carrying forward') and pairs with 'recall' and 'forget' as alternatives, providing clear usage guidance.

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

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, destructiveHint. The description adds significant detail: internal cascading through multiple endpoints, specific return fields per type (ticker, CIK, RxCUI, etc.), and citation URIs. 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?

Well-structured with front-loaded purpose and usage guidance. Every sentence adds value, though slightly verbose; could be condensed slightly without losing information.

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

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

Despite no output schema, the description fully explains return values for both entity types and internal behavior. It covers usage, parameters, and output comprehensively, making it complete for this tool's complexity.

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

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

Schema already covers 100% of parameters with descriptions. The description enriches them with concrete examples (e.g., 'AAPL', 'ozempic') and explains auto-disambiguation, adding meaning beyond the schema's basic type definitions.

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

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

The description clearly states it resolves user-spoken names to canonical identifiers, provides example queries, and distinguishes itself from sibling tools by being the go-to tool for ID lookup before using other 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 'Use FIRST whenever you have a name but need an ID', providing strong usage context. However, it does not explicitly list when not to use or name alternative tools for when an ID is already known.

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=false. The description adds that it probes each entity with 'ai_visibility_check' and returns a ranked list with score, confidence, and signal density. These details go beyond annotations, fully disclosing the composite nature and output format.

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 that front-load the main purpose and key outcomes. Every sentence adds value without 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's complexity (4 parameters, no output schema), the description explains the process (probing ai_visibility_check), the output (ranked list with fields), and the use-case. It does not detail sorting order or score calculation, but for a comparison tool, this is sufficient for an agent to understand and invoke correctly.

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

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

Schema description coverage is 100%, so each parameter is well-documented. The description adds context that the first entity in 'entities' is treated as the 'subject' for narrative, and explains how 'models' and '_apiKey' relate to probing. This adds meaningful value beyond the schema.

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

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

The title and description clearly state the tool compares AI visibility across multiple entities, ranks them, and surfaces which is most/least recognized. The example use-case and reference to 'competitive AI-marketing audits' provide specific context. It differentiates from sibling tools like 'ai_visibility_check' by being a composite comparison 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?

The description explicitly states it is useful for competitive audits and gives an example question. It implies that for a single entity check, one should use the underlying 'ai_visibility_check' tool. However, it does not explicitly list alternatives or caveats for when not to use this tool.

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

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

Annotations already declare readOnlyHint, idempotentHint, etc. The description adds valuable behavioral context: partial failures degrade gracefully, bundlephobia's first measurement can take 5-30s, and sources_failed will list timeouts. 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 dense but well-structured with front-loaded purpose, followed by usage guidance, ecosystem notes, and behavioral details. Could be slightly more concise, but every sentence adds value.

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

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

Despite lacking an output schema, the description thoroughly explains the return fields (summary block, per-advisory detail, links, alternative versions). It also covers edge cases like scoped packages and partial failures.

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 meaning beyond schema: scoped packages accepted, version defaults to latest when omitted. This justifies a 4.

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

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

The description clearly states it's a composite check for adding npm packages, combining deps.dev and bundlephobia data. It uses specific verbs like 'scan' and 'check' and distinguishes itself from sibling tools by its unique composite nature.

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 agent asks about safety/popularity/size or cost of adding a package. Also notes ecosystem limitations (NPM v1) and provides alternative for other ecosystems via deps.dev:version directly.

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

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

Annotations fully cover safety (readOnly, idempotent) and scope (openWorld). The description adds no behavioral context such as pagination, rate limits, or result scope. With annotations present, the description fails to add value.

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

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

The description is a single, efficient sentence with zero wasted words. It is front-loaded and direct.

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, an output schema, and multiple siblings, the description is insufficient. It omits details about clustering, result format, and when to use alternatives.

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 67%; 'query' lacks a description. The tool description does not add parameter meaning beyond what schema provides. The parameter 'query' is self-explanatory, so baseline 3 is appropriate.

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

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

The description clearly states the verb 'Search' and the resource 'all Reactome objects'. While generic, it distinguishes from sibling tools like 'search_within' by implying a broad 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?

No guidance is provided on when to use this tool versus alternatives (e.g., search_within, deep_research). The annotations hint at safe usage but do not explain context.

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

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

Annotations already provide readOnlyHint, openWorldHint, idempotentHint. The description adds behavioral details beyond annotations: 'BGE-base-en embeddings + cosine over 500-char overlapping windows; cap is 200K chars (longer inputs are truncated and flagged).' This explains the underlying mechanism and limits, which is valuable context that supplements 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 a single, well-structured paragraph of four sentences. It is front-loaded with the core function, then elaborates on use cases, pairing, and technical details. Every sentence adds value without redundancy, achieving conciseness without sacrificing 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 the tool has 3 parameters, exhaustive annotations, and no output schema, the description covers most essential aspects: purpose, usage context, technical details (embeddings, windowing, truncation), and complementary tool. It does not explicitly describe the return structure beyond mentioning 'passages with character offsets and similarity scores,' but this is sufficient for an AI agent to understand the output. Slight deduction for not stating whether results are paginated or limited further.

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

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

Schema description coverage is 100%, meaning each parameter already has a description. The description does not add significant new meaning beyond summarizing the schema: it reiterates the 200K char limit for 'text' and gives example queries for 'query'. The baseline is 3; the description provides minor enhancement but no additional semantic depth.

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 specific verb-resource pairing: 'Semantic search INSIDE a fetched record.' It clearly states what it does (search inside text) and distinguishes itself from siblings by noting it 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?

The description explicitly states when to use: 'Use when the record is too big to cram into the prompt.' It also explains benefits (saves context, returns passages with offsets for verification) and mentions a complementary tool (ask_pipeworx_grounded), providing clear guidance on when to choose this tool over 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 include idempotentHint=true but no destructive hint. The description adds behavioral details beyond annotations: requiring a Pipeworx OAuth account, SMS 10/day cap, webhook HMAC signing and auto-disable after 10 failures. No contradictions with annotations.

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

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

The description is somewhat long but front-loads the core purpose in the first sentence. Each subsequent sentence adds necessary detail on types, parameters, and delivery. While efficient, some redundancy could be trimmed (e.g., repeating delivery details in the delivery property description).

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

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

Given the tool's complexity (multiple subscription types, delivery channels, account requirements), the description covers all essential aspects: types, parameters, required account, delivery constraints, and return of subscription id. No output schema exists, so return value is adequately described. Minor gaps: no mention of error codes or failure 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%, baseline 3. The description adds meaning by providing concrete examples for each subscription type's parameters and delivery options, and explaining conditions like phone verification and webhook signing. This adds context beyond the schema's property descriptions.

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

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

The description clearly states the verb 'Create', the resource 'proactive monitoring subscription', and the data source 'live-data event stream'. It lists supported types and mentions returning the subscription id, which distinguishes it from sibling tools like 'unsubscribe' and 'list_subscriptions'.

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

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

The description provides explicit context on when to use: 'Create a proactive monitoring subscription...' and explains supported types and delivery options. It also notes that anonymous/BYO accounts cannot persist subscriptions, but does not explicitly exclude alternatives or give 'when not to use' guidance.

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

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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint. The description adds valuable behavioral context: it's an onboarding tool that returns examples and can be filtered by topic. No contradictions. It discloses the return structure (category-bucketed questions with tool+argument shapes) even without an output schema.

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

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

The description is long but well-structured, starting with trigger phrases in a list, then explaining output and usage. Every sentence adds value, though it could be slightly more concise. The front-loading of trigger phrases helps quick recognition.

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 compensates well by describing the returned examples and their structure. It covers when to use, how to filter, and the intent. It is complete enough for an agent to understand what to expect.

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

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

Schema coverage is 100% with one optional parameter 'topic'. The description adds meaning beyond the schema by explaining that omitting the parameter gives a full spread, and it lists possible values again. This helps the agent understand the parameter's effect better than the schema alone.

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

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

The description clearly states the tool's purpose: it returns category-bucketed example questions with exact tool+argument shapes. It distinguishes itself as the onboarding entry point and lists specific categories (e.g., company financials, drugs), making it distinct from siblings 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 states when to use: 'Use this FIRST when you do not yet know what Pipeworx can do for you, or to learn how to call the meta-tools'. Explains the topic parameter and its effect. Does not explicitly list exclusions or when not to use, but provides strong contextual 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?

Beyond annotations (destructiveHint=false), the description reveals that the row is deactivated (not deleted) and historical events remain. 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?

Three focused sentences, no wasted words. Essential information front-loaded.

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

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

Given low complexity, no output schema, and full schema coverage, the description adequately covers the tool's behavior and effect.

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

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

The schema covers 100% of parameters with description. The description adds ownership context but no new syntactic details. Baseline 3 is appropriate.

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

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

The description clearly states the action ('Cancel a subscription by id') and identifies the resource (subscription). It distinguishes from siblings like 'subscribe' and 'list_subscriptions' by specifying the inverse operation.

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

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

The description mentions ownership enforcement ('you can only cancel your own subscriptions'), which guides usage. It lacks explicit when-not-to-use or alternatives, but 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?

Annotations provide readOnlyHint, openWorldHint, idempotentHint, destructiveHint. The description adds useful behavioral context: returns a verdict with types, uses SEC EDGAR + XBRL, and provides a citation. 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 key phrases and is efficiently structured. It could be slightly more concise, but every sentence adds value, and it avoids unnecessary repetition.

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

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

Despite no output schema, the description thoroughly explains return values (verdict types, citation, percent delta) and supported domains. It provides complete context for an agent to use the tool correctly.

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

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

The input schema has 100% description coverage for the single 'claim' parameter. The description adds context about expected format and examples, 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 the tool's purpose: natural-language claim verification against authoritative sources, specifically for company-financial claims. It distinguishes itself from sibling tools by being a dedicated fact-check tool that replaces multiple 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?

The description explicitly says 'Use whenever the agent needs to check whether something a user said is factually correct' and mentions that it replaces 4-6 sequential calls. While it doesn't explicitly list when not to use, the guidance is clear and actionable.

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