Pubchem

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

No annotations are provided, so the description carries the full burden. It explains that Pipeworx picks the right tool, fills arguments, and returns results, and lists many data sources. However, it does not disclose behavioral traits such as rate limits, authentication needs, or what happens if the question is ambiguous or no source matches. This is a moderate disclosure.

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

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

The description is somewhat lengthy but well-structured, starting with the main purpose, then usage guidance, followed by examples. It is front-loaded and every sentence adds value, though a slightly more concise version could improve readability.

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

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

Given the tool has a single parameter, no output schema, and no annotations, the description covers the purpose, usage, and examples thoroughly. It could mention failure modes or limitations, but overall it is sufficiently complete for an AI agent to understand the tool's capabilities.

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

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

The input schema has 100% coverage with a clear description for the single 'question' parameter. The description adds value by providing context and examples of valid questions, going beyond the schema's 'natural language' description.

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

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

The description clearly states that this tool answers natural-language questions by automatically selecting the appropriate data source. It provides specific verb-resource combinations like 'What is X?', 'Look up Y', and 'Find Z', and distinguishes itself from sibling tools (e.g., compare_entities, discover_tools) which are more specialized.

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 when a user asks...' and provides clear examples of query types. It does not explicitly state when not to use it or suggest alternatives, but the context implies it is the go-to tool for general questions, making the guidance adequate but not exhaustive.

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

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

Without annotations, the description carries the full burden. It discloses data sources (SEC EDGAR/XBRL for companies; FAERS, FDA, trials for drugs) and return type (paired data + citation URIs). It does not mention if the tool is read-only or any side effects, but the context implies no mutation. No contradictions with annotations (none provided).

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

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

The description is concise (5 sentences) with no wasted words. It front-loads the core purpose and usage, then provides details on types and what data to expect. Every sentence adds value.

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

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

Given the tool's complexity (two entity types, multiple data points) and the absence of an output schema, the description covers most necessary context: supported types, data sources, and use cases. However, it does not explain the return format in detail or pagination/citations beyond URIs, leaving minor ambiguity.

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

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

The input schema already has 100% description coverage, providing baseline 3. The description adds meaningful context by explaining what data is pulled for each 'type' (e.g., revenue, net income for companies; adverse events for drugs) and the format for 'values' (tickers vs drug names). This goes beyond the schema's minimal descriptions.

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

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

The description clearly states the verb 'compare' and the resource '2–5 companies (or drugs)', making the tool's purpose immediately obvious. It distinguishes itself from sibling tools (e.g., search, profile) by explicitly noting it replaces 8–15 sequential agent calls, so the agent knows when to use it.

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 triggers like 'compare X and Y', 'X vs Y', and specific use cases (revenue, adverse events). However, it does not mention when NOT to use this tool (e.g., if the user wants a single entity or more than 5 items), slightly lowering the score.

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

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

No annotations are provided, so the description carries the full burden. It states that the tool 'Returns the top-N most relevant tools with names + descriptions.' This is useful but lacks details on how relevance is determined, whether results are sorted, or if there are limitations (e.g., only top-20 default). Some behavioral transparency is present, but not exhaustive.

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

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

The description is relatively concise given its scope, with most sentences adding value. It front-loads the core action ('Find tools by describing the data or task') and then provides examples and usage guidance. It could be slightly trimmed, but it's well-structured and not overly 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?

For a discovery tool with many siblings, the description is fairly complete: it explains what it does, when to use it, and what to expect in return (top-N relevant tools with names and descriptions). There is no output schema, but the description suffices. It could mention pagination or result format, but overall it covers the essential context.

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

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

Schema description coverage is 100% for both parameters (query and limit). The description adds context by providing example queries for the 'query' parameter, but this largely supplements rather than adds new meaning. The description does not elaborate on the 'limit' parameter beyond what the schema says. Baseline 3 is appropriate.

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

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

The description clearly states the tool's purpose: to find tools by describing data or task. It lists numerous domains (SEC filings, financials, FDA drugs, etc.) and includes a clear verb+resource structure ('browse, search, look up, or discover what tools exist'). It distinguishes itself from sibling tools (which are mostly entity lookups or feedback) by being a discovery 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 says 'Call this FIRST when you have many tools available and want to see the option set (not just one answer).' This provides direct guidance on when to use the tool. While it doesn't explicitly state when not to use it, the context makes it clear that this is for exploration rather than targeted lookups.

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

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

No annotations provided, but the description fully discloses the return data (SEC filings, fundamentals, patents, news, LEI, citation URIs). It implies a read-only operation, though not explicitly stated. No side effects mentioned but context suggests safe read.

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

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

The description is well-structured with purpose first, then usage examples, then output details. Slightly verbose but packs necessary information without redundancy.

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

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

No output schema exists, but the description enumerates what is returned. Does not mention pagination or limitations, but given the compound nature of the tool, it provides sufficient context for an agent to understand its capabilities.

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

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

Schema coverage is 100% and descriptions are present. The tool description adds value by explaining the 'type' enum only supports 'company' and clarifying that 'value' accepts ticker or CIK, not names, with a reference to resolve_entity.

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 'Get everything about a company in one call', specifying the verb and resource. It distinguishes from siblings by mentioning the alternative 'resolve_entity' for name resolution.

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

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

Explicitly lists example user queries and when to use this tool (e.g., 'tell me about X') and when not to (e.g., using resolve_entity for names). Provides clear context for usage.

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

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

No annotations are provided, so the description must reveal behavior. It states 'delete,' implying a destructive action, but lacks details on irreversibility, error handling, or permissions. Adequate for a simple operation but not exhaustive.

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 that front-load the purpose and immediately provide usage guidance and pairing. No redundant words; every sentence earns its place.

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

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

Given the simplicity (one param, no output schema, no annotations), the description covers purpose, usage, and sibling relationships. Missing details on return values or confirmation, but it is sufficient for a basic delete tool.

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

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

The input schema covers 100% of parameters with a description for 'key.' The description only echoes 'by key,' adding no extra meaning beyond what the schema already provides.

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

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

The description clearly states 'Delete a previously stored memory by key,' specifying the verb 'delete' and the resource 'memory.' It distinguishes from sibling tools 'remember' and 'recall' by focusing on deletion.

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

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

Explicitly lists conditions for use: 'when context is stale, the task is done, or you want to clear sensitive data.' Also suggests pairing with 'remember' and 'recall,' providing clear alternatives.

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

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

The description does not disclose behavioral traits beyond the purpose. With no annotations provided, the agent is left uninformed about potential constraints, permissions, or side effects. For a retrieval tool, it would benefit from stating it is read-only.

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

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

The description is a single, concise sentence with a usage hint, front-loading the key information without extraneous text.

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 (single parameter, no output schema), the description is mostly complete. It could mention the format of the returned classification tree, but it is adequate for an agent to understand the tool's purpose.

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

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

Schema coverage is 100% and the description only adds minor context ('for a CID'). The parameter is well-documented in the schema, so the description adds marginal value, meeting the baseline.

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

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

The description clearly states it returns a pharmacological classification tree for a CID, listing drug class, mechanism, and biological role tags. It distinguishes from sibling tools like get_compound by focusing on classification rather than generic compound data.

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 mentions it is useful for 'what kind of drug is X' questions, providing clear context. However, it does not mention when not to use it or alternatives (e.g., get_compound for detailed properties).

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

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

No annotations are provided, so the description carries full burden. It transparently lists the returned properties and implies a read-only operation. However, it does not disclose potential errors, authentication needs, or rate limits, but for a simple get operation, this is acceptable.

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 sentence listing many properties, which is relatively concise but slightly long. It could be broken into bullet points for better readability, but it is front-loaded with the purpose.

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

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

Given one parameter and no output schema, the description comprehensively covers the output by listing numerous properties. It does not mention errors or pagination, but for a simple retrieval tool, it is sufficiently complete.

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

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

Schema coverage is 100%, with 'cid' well-described as PubChem Compound ID. The description adds context by listing output properties, which indirectly clarifies the parameter's role, but does not add new semantic information beyond the schema.

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

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

The description clearly states the tool retrieves standard properties for a PubChem CID and lists specific properties like molecular formula, weight, IUPAC name, etc. It distinguishes from siblings like get_classification and get_synonyms by focusing on compound-specific data.

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

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

The description implies usage for retrieving compound properties but provides no guidance on when to use this tool over siblings. It does not mention alternatives or exclusions.

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

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

With no annotations, the description carries the burden. It lists types of names but does not disclose behavior such as result limits (max_results is described only in schema), pagination, rate limits, or whether the list is exhaustive. The description adds value but leaves gaps.

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

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

The description is a single, concise sentence that efficiently conveys the tool's purpose. Every word earns its place, with no unnecessary details.

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

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

Given no output schema, the description should clarify the return format (e.g., list of strings). It does not explain how results are structured or if max_results affects output. The description is adequate for a simple list but lacks completeness for an agent to anticipate output.

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

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

Schema coverage is 100%, so baseline is 3. The description adds no additional meaning beyond the schema: cid is already described as 'PubChem Compound ID' in schema, and max_results is only described in schema as 'Cap (default 50)'. The description does not elaborate on parameter behavior.

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

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

The description clearly states the tool lists all names (synonyms) for a CID, with specific examples like common names, IUPAC, trade names, and CAS numbers. It distinguishes itself from sibling tools, none of which focus on synonyms.

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

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

The description implies use for retrieving synonyms but does not specify when to use this tool versus alternatives. No explicit guidance on when not to use it or prerequisites like CID availability.

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

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

With no annotations, description fully covers behavioral traits: rate-limited to 5 per identifier per day, doesn't count against quota, free, and that the team reads digests daily and feedback affects roadmap. 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 a single coherent paragraph that front-loads the core purpose and includes all necessary details. Although informative, it could be slightly more structured with bullet points for readability, but it remains efficient and 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?

For a feedback tool with 3 parameters, nested object, and enum, the description covers purpose, usage guidelines, behavioral transparency, and parameter semantics comprehensively. It leaves no gaps for an agent to misuse the tool.

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

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

Schema coverage is 100%, but description adds significant meaning beyond enum values by explaining when each 'type' applies (e.g., 'bug = something broke or returned wrong data'). It also clarifies the 'message' parameter should be specific about tools/errors and mentions 2000 char max.

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 giving feedback (broken, missing, or needs to exist) to the Pipeworx team. It explicitly lists feedback types (bug, feature, data_gap, praise) and distinguishes itself from sibling tools like ask_pipeworx, discover_tools, etc.

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

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

Description explicitly says when to use: when a tool returns wrong/stale data, when a desired tool is missing, or for praise. It also provides when-not-to-use guidance (don't paste end-user prompt) and mentions rate limits and that it's free, guiding appropriate usage.

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

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

No annotations provided, so description carries full burden. Adds scoping info (identifier-based) and omitting key lists all keys. Does not disclose error behavior for missing keys or return details.

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

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

Three sentences, each providing essential information: action, use case, and scoping/pairing. No redundant or irrelevant content.

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

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

No output schema, but description does not specify return format or error handling. Covers scoping and optional key behavior, but missing details on what is returned for list vs. single retrieval. Adequate for a simple tool but could be more complete.

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

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

Schema coverage is 100%, with a clear description for 'key' parameter. Tool description largely repeats the schema's behavior for omitting key. Adds no new parameter-level details beyond that.

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 tool retrieves a saved value or lists all keys, with a specific verb (retrieve/list) and resource (saved values). Distinct from siblings '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?

Explicitly advises using to look up context saved earlier without re-deriving, and pairs with 'remember' and 'forget'. Lacks explicit 'when not to use' but is clear about scope and pairing.

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 fan-out to SEC EDGAR, GDELT, USPTO and return structure. No annotations provided, so description does the work, but omits potential limitations like rate limits or data latency.

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, well-structured, front-loaded with purpose. Every sentence adds value with examples and details. No redundancy.

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

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

Covers the multi-source nature and return format. No output schema, so description compensates. Could mention aggregation or performance, but sufficient for a moderately complex tool.

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

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

Schema covers all 3 parameters with descriptions, so baseline is 3. Description adds little beyond repeating schema info (e.g., date formats). No new parameter 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?

Description clearly states the tool retrieves recent changes for a company, with specific example queries. However, it does not explicitly distinguish from sibling tools like entity_profile or compare_entities.

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

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

Provides multiple example user queries and context for when to use. Lacks guidance on when not to use or explicit 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?

Given no annotations, the description discloses key behavioral traits: key-value storage scoped by identifier, persistence differences (authenticated vs anonymous 24-hour memory). Does not cover all edge cases but sufficient.

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 purpose, then usage, technical details, and pairing. 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 write tool with 2 required params and no output schema, the description covers use cases, storage details, lifetime, and technology pairing. 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?

Input schema covers 100% of parameters with descriptions. Description adds value by providing examples of key/value types and context beyond schema.

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

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

The description clearly states the tool saves data for reuse, with specific verb 'save' and resource 'data'. It distinguishes from siblings 'recall' and 'forget' by mentioning pairing.

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

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

Explicitly states when to use 'when you discover something worth carrying forward' with examples. Mentions pairing with recall/forget but does not explicitly state when not to use.

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

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

No annotations provided, so description carries full burden. It discloses return values (IDs plus pipeworx:// citation URIs). As a read-only lookup, it is adequately transparent, though it does not mention failure modes or limitations.

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

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

Five sentences, well-structured, front-loaded with purpose, includes examples and usage guidance. No redundant 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?

Given the tool's simplicity (2 params, simple lookup), the description fully explains purpose, parameters, return values, and usage context. No output schema, but return values are described. Complete and self-contained.

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%, giving baseline 3. Description adds value by explaining the meaning of parameters with examples (e.g., 'Apple' → AAPL for company, 'ozempic' for drug) and clarifying legitimate inputs for value.

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

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

Description clearly states the tool looks up canonical/official identifiers for companies or drugs, listing specific ID systems (CIK, ticker, RxCUI, LEI). Examples provide concrete demonstrations. Distinguishes itself by specifying it should be used before other tools needing official identifiers.

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 a user mentions a name and you need the CIK...' and 'Use this BEFORE calling other tools that need official identifiers.' Implies when-not-to-use, but does not mention sibling alternatives like entity_profile or search_by_name.

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

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

No annotations provided, so description carries full burden. States it returns CIDs but doesn't disclose behavior beyond that (e.g., no side effects, auth needs, rate limits). Safe read operation is implied but not explicit. Adequate but minimal.

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

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

Three concise sentences: purpose, usage examples, and next step. No redundancy or fluff. Front-loaded with key action. Every sentence earns its place.

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

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

Given simple tool with full schema coverage and no output schema, description explains purpose and next steps. Minor gap: does not specify return format (e.g., list of CIDs or objects). Otherwise complete for its complexity.

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

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

Schema description coverage is 100% with clear parameter descriptions. Description adds that it returns CIDs matched to name, but does not add extra parameter-level semantics beyond schema. Baseline 3 is appropriate.

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

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

Description clearly states purpose: resolve chemical/drug names to PubChem CIDs. Specific verb 'resolve' and resource 'PubChem CIDs' differentiate from siblings like get_compound (properties) and get_synonyms (synonyms). Examples reinforce understanding.

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

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

Explicitly says 'Use for "what's the CID of ibuprofen?" or to disambiguate' and advises subsequent use of get_compound. Provides clear context, though no explicit when-not cases are given; siblings imply 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?

No annotations provided, so description carries burden. It describes the return values (verdict, extracted form, actual value with citation, percent delta) and notes it replaces multiple sequential calls. No contradictions. Could add error handling details.

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

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

Front-loaded with main action and usage, then provides details on scope, return types, and efficiency. Every sentence adds value without redundancy.

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

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

Comprehensive for a single-param tool: explains purpose, domain, return structure, and efficiency. Missing explicit handling for out-of-scope claims or errors, but overall 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?

The sole parameter 'claim' is well-described in the schema with examples. The description adds context about supported domain and format, enhancing understanding beyond the schema.

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

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

Description clearly states it validates factual claims against authoritative sources, with specific examples like 'Is it true that...'. The tool is distinct from siblings such as ask_pipeworx or compare_entities, which serve different purposes.

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

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

Provides explicit use cases (e.g., 'Verify the claim that...') and notes the v1 limitation to company-financial claims. Does not explicitly state when not to use, but the context implies domain restriction.

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