Pharma Intel

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

No annotations are provided, so the description carries full burden. It reveals that the tool selects the best data source and fills arguments, but does not disclose failure modes, latency, or which tools it might call. This is adequate but not detailed.

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 (three sentences) with examples front-loaded. Every sentence adds value, though it could be slightly tighter without losing meaning.

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 set and absence of output schema, the description is sufficiently complete. It clarifies the tool's role as an orchestrator, which is important given the sibling tools that are domain-specific.

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

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

Schema coverage is 100% for the single parameter 'question'. The description adds value by explaining how the parameter is used (natural language request) and giving examples, but the schema already describes it as a string for the user's question.

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 accepts natural language questions and returns answers by selecting appropriate data sources. It distinguishes from siblings by explicitly positioning itself as an intelligent orchestrator that abstracts away tool selection and schema details.

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 it ('just describe what you need') and provides concrete examples. However, it does not explicitly state when not to use it or compare to alternatives, leaving some ambiguity.

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

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

With no annotations provided, the description carries full burden. It discloses that the tool returns paired data and resource URIs, and implies a read operation. However, it does not explicitly state that it has no side effects or destructive actions, leaving some ambiguity.

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

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

Three sentences front-load the purpose, efficiently cover key details, and contain no fluff. 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?

Without an output schema, the description reasonably explains the return data for each type and mentions resource URIs. It could be more specific about the return format, but given the complexity of a comparison tool with two distinct use cases, it is adequately 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%, and the description adds substantial context: it explains the enum values (company vs drug) with specific data fields returned, and for the 'values' parameter, it provides examples and clarifies expected formats (tickers/CIKs for company, drug names for drug). 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 'entities side by side in one call'. It distinguishes between two entity types (company and drug) with specific data fields, and mentions it replaces 8-15 sequential calls, making it distinct from siblings like pharma_drug_profile which focus on single entities.

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

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

The description implies efficiency by noting it replaces multiple sequential calls, but lacks explicit guidance on when to use alternatives or when not to use this tool. Siblings like pharma_drug_profile exist, but no differentiation criteria are 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?

No annotations are provided, so the description carries full burden. It discloses that it returns tool names and descriptions, but does not mention potential behavior like the quality of search results, whether it uses semantic search, or any limitations like rate limits. A score of 3 is appropriate as it provides basic but not comprehensive behavioral context.

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

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

The description is three sentences long, each adding value: first defines purpose, second describes output, third gives usage guidance. It is concise and front-loaded. However, the last sentence could be slightly more concise by combining with the previous, but overall very efficient.

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

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

Given the tool's simplicity (search, return list), the description is mostly complete. No output schema exists, so the description should indicate what is returned (it does: tool names and descriptions). It covers the primary use case and guidance. Could mention that results are sorted by relevance, but not strictly necessary.

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

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

Schema description coverage is 100%, so baseline is 3. The description does not add extra meaning beyond what the schema provides, as it only describes the tool's overall purpose. No additional parameter details are given, so score remains at 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 searches a catalog and returns relevant tools, using specific verbs ('Search', 'Returns') and resource ('Pipeworx tool catalog'). It distinguishes itself by instructing to call this FIRST when many tools are available, differentiating from sibling tools that perform specific tasks like pharma lookups.

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

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

Explicitly says 'Call this FIRST' when 500+ tools are available, providing clear when-to-use guidance. It does not need to mention when not to use since its purpose is discovery before other tools, and siblings are specific domain tools, so the guidance 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?

With no annotations, description carries full burden. It discloses that the tool returns pipeworx:// citation URIs and replaces multiple sequential calls. Does not mention potential performance issues or failure modes, but is otherwise transparent.

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 pack all essential information: purpose, data sources, and alternatives. No redundant words.

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

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

Despite no output schema, description explains return type (citation URIs). Covers inputs, use cases, and alternative tools. Complete for a tool bundling multiple data sources.

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 description adds context beyond schema: specifies that type is only 'company' for now, explains value formats (ticker or zero-padded CIK), and warns that names are not supported.

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 that the tool returns a full profile of an entity across multiple Pipeworx packs, listing specific data sources (SEC filings, XBRL, USPTO, GDELT, LEI). It distinguishes itself from siblings by noting federal contracts should use usa_recipient_profile.

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

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

Explicitly states when to use (for company type) and when not to use (for federal contracts, pointing to alternative tool). Also advises to use resolve_entity if only a name is 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?

No annotations provided, so description carries full burden. It correctly indicates destructive behavior ('Delete'), but lacks details on irreversibility, confirmation, or side effects.

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

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

Single concise sentence front-loading the action and target. No unnecessary words, but could include a brief usage note without losing 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?

For a simple 1-parameter tool with no output schema, the description is adequate. However, it lacks context about confirmation, error handling, or impact on related data.

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

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

Schema description coverage is 100% for the single required parameter 'key', with a clear description. The tool description adds no further meaning beyond what the schema provides, baseline score 3.

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

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

The description clearly states the action ('Delete') and the target ('a stored memory by key'). It is unambiguous and distinct from siblings like 'remember' (store) and 'recall' (retrieve).

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 (e.g., 'recall' for retrieval, 'remember' for storage). No mention of prerequisites or when deletion is 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 are empty, so description carries full burden. It indicates the tool is a read operation (fetches data) and lists what data is returned. However, it does not disclose potential rate limits, data freshness, or whether the call might be slow due to aggregating multiple sources.

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: first lists what the tool returns, second provides input format with examples. No wasted words, but could be slightly more structured (e.g., bullet points) 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 simple input schema (1 string param) and no output schema, the description provides a good overview of what the tool returns. It covers the main use case. Could mention that the output is a single object with multiple fields, but not necessary for completeness.

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

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

Schema description coverage is 100% for the single parameter, which already describes 'drug_name' as 'Drug name (brand or generic)'. The description adds examples and context that it accepts brand or generic names, enhancing semantics 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 returns a comprehensive drug dossier including FDA approvals, labels, adverse events, RxNorm properties, interactions, and clinical trials. It specifies the input as a drug name with examples. This differentiates it from siblings like pharma_pipeline_scan and pharma_safety_report.

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 implies usage when a comprehensive drug profile is needed, but does not explicitly state when to use this vs. alternatives like pharma_safety_report. No exclusions or context 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?

With no annotations provided, the description carries the full burden. It discloses the return categories (trial counts, recruiting studies, approved drugs) but does not mention whether the data is real-time or cached, any rate limits, or the scope of the database. No contradiction with annotations as annotations are empty.

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

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

The description is two sentences long, front-loads the key action ('pipeline analysis'), and efficiently conveys filtering options and return types. It could be slightly more structured (e.g., bullet points) but is concise and scannable.

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

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

Given the tool's moderate complexity (two optional parameters, no output schema, no nested objects), the description covers the main aspects: purpose, filters, and return categories. It lacks details on whether results are aggregated or individual, but the provided information is sufficient for an agent to decide to use it.

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

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

Schema coverage is 100%, meaning the schema already describes both parameters adequately. The description adds context by providing example values (e.g., 'lung cancer', 'Pfizer') and clarifying that at least one parameter is expected, but it does not add meaning beyond what the schema already provides. Baseline 3 is appropriate.

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

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

The description clearly states the tool's purpose: clinical trial pipeline analysis. It specifies the two primary filtering dimensions (condition and sponsor) and explicitly lists what results are returned (trial counts, recruiting studies by phase, FDA-approved drugs), making it highly specific and distinguishing it from sibling tools like pharma_drug_profile.

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

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

The description provides clear context on when to use this tool: for pipeline analysis by condition or sponsor. It implicitly excludes other sibling tools (e.g., pharma_drug_profile for individual drug details), but does not explicitly state when not to use it or mention alternatives. The examples of condition and sponsor values are 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?

No annotations provided, so description carries full burden. It clearly states this is a read operation and lists what data is returned, but lacks details on rate limits or authentication.

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 sentence with bullet-style list of functions, no wasted words, and essential information is front-loaded.

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

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

Given low complexity (1 param, no nested objects, no output schema), description is adequate but could mention output format (e.g., JSON) or any limitations.

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

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

Schema coverage is 100% and description says 'Provide a drug name', which adds no extra meaning beyond the schema's description 'Drug name (brand or generic)'. 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?

Description clearly lists specific actions (adverse event reports, top reaction types, recall history, drug-drug interactions) and requires a drug name, distinguishing it from sibling tools like pharma_drug_profile and pharma_pipeline_scan.

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 implies use for drug safety assessment and lists what it covers, but does not explicitly state when to use this tool vs siblings (e.g., pharma_drug_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?

No annotations are provided, so the description carries the full burden. It discloses rate-limiting (5 per identifier per day) and content rules. It does not specify whether feedback is processed synchronously or if there is a confirmation response, but overall provides decent transparency for a feedback tool.

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

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

The description is only three sentences, front-loaded with the action and use cases. Every sentence adds value with no redundancy or fluff.

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

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

For a feedback tool with 3 parameters and no output schema, the description provides enough context: purpose, allowed input types, content guidelines, and rate limits. It could mention what the agent should expect after sending (e.g., no immediate response), but overall it is sufficient for an agent to select it appropriately.

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

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

Schema description coverage is 100%, so the baseline is 3. The description reinforces the message parameter's guidance but does not add substantial new information beyond what the schema already provides. It adds context like 'describe in terms of Pipeworx tools/data' which is helpful but not essential.

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 sends feedback to the Pipeworx team and lists specific use cases (bug reports, feature requests, missing data, praise). This distinguishes it from sibling tools which focus on data querying, discovery, or memory management.

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 tells when to use the tool (for various types of feedback) and provides a negative guideline (do not include end-user's prompt verbatim). It also mentions rate limits. However, it does not explicitly exclude situations like asking questions that are better suited for ask_pipeworx, but the context makes that clear.

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

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

No annotations are provided, so the description carries the burden. It explains the two modes (key vs no key) but does not disclose potential side effects, persistence behavior, or access patterns. Given no annotations, a 3 is appropriate for covering basic 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?

Description is two sentences, front-loaded with the core action. No wasted words. Could be slightly more concise by merging the second sentence into the first, but still effective.

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

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

Tool is simple (1 optional param, no output schema, no nested objects). The description covers the essential usage scenarios. However, it doesn't mention what format the returned memory takes (string, object) or whether listing returns keys only or full memories. For a simple retrieval tool, this is adequate but not fully complete.

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

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

Schema description coverage is 100%, so the schema already documents the 'key' parameter. The description adds the meaning that omitting key lists all memories, which is already implied by the schema's required: [] and property description. Baseline 3 is correct.

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 memory by key or lists all memories when key is omitted. The verb 'retrieve' and resource 'memory' are specific. It distinguishes itself from siblings like 'remember' (store) and 'forget' (delete).

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 for when to use: to retrieve context saved earlier. Implicitly contrasts with 'remember' and 'forget' but does not explicitly 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, description carries full burden. It discloses that type='company' fans out to SEC EDGAR, GDELT, USPTO in parallel. Also mentions return format: structured changes, total_changes count, and URIs. Adequate for a read tool; no destructive actions or auth issues.

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 efficient sentences, front-loaded with purpose. Each sentence adds critical detail: fan-out behavior, date formats, return values, and use cases. No waste.

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

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

Given tool complexity (fan-out to three sources), description fully covers behavior, parameters, and output shape. No output schema, but return fields are described. Sufficient for correct invocation.

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

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

Adds significant value beyond 100% schema coverage. Provides examples for 'since' (ISO and relative), suggests '30d' for monitoring, and clarifies 'value' (ticker or CIK). Explains that type='company' triggers fan-out 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?

Description clearly states the tool's purpose: 'What's new about an entity since a given point in time.' It specifies the verb (query changes) and resource (entity), with explicit fan-out behavior for company type. Distinct from sibling tools like entity_profile (static profile) and compare_entities.

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

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

Explicitly states use cases: 'brief me on what happened with X' or change-monitoring workflows. Does not explicitly list when not to use, but context is clear. Could improve by naming sibling alternatives for other entity types.

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 mentions persistence differences between authenticated and anonymous sessions, but does not disclose details like overwrite behavior, storage limits, or whether values are private.

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 serving a distinct purpose: what the tool does, when to use it, and persistence behavior. 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?

Given the tool's simplicity (2 parameters, no output schema), the description covers core functionality well. Missing details like overwrite behavior or storage limits are minor gaps for a simple key-value store.

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 detailed descriptions for both parameters (key and value). Description adds value by explaining the purpose (session memory) and providing example keys, but does not add significant semantics 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 explicitly states 'Store a key-value pair in your session memory', uses specific verb ('store') and resource ('key-value pair'), and clearly distinguishes from siblings like 'forget' 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 usage context: 'save intermediate findings, user preferences, or context across tool calls'. Does not explicitly state when not to use it, but the examples implicitly guide appropriate 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 implies a read operation (returns data), but does not explicitly state if it is read-only, error handling, or safety. Adequate but could be more explicit.

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 bullet list of output items. No wasted words, front-loaded with core purpose. Easy to parse.

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

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

For a simple lookup tool with 2 parameters and no output schema, description covers purpose, inputs, and outputs. Lacks details on errors or rate limits, but sufficient for basic usage.

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 (100%). Description adds value by explaining that 'value' can be ticker, CIK, or name, and gives concrete examples. Adds 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?

Clearly states it resolves an entity to canonical IDs across Pipeworx data sources in a single call. Specifies entity type 'company' with examples (ticker, CIK, name). Distinct from all sibling 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?

Describes when to use: replaces 2-3 lookup calls. Provides example inputs and output components. Does not explicitly state when not to use, but 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?

Describes returns (verdict, citation, delta) and mentions it's read-only by nature, but doesn't disclose limitations (only US public companies, only SEC EDGAR data) or failure modes. No annotations provided, so description carries full burden.

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

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

Two sentences, front-loaded with purpose, every sentence adds value. No wasted words or repetition.

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

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

Given single parameter, no output schema, and no annotations, description thoroughly explains functionality, return values (verdict, value, citation, delta), and scope. Meets completeness for this complexity level.

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

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

Schema coverage 100%; description adds example formats for the claim parameter but no additional semantic constraints beyond the schema. Baseline 3 is appropriate.

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

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

Description clearly states it fact-checks natural-language claims against authoritative sources, specifies v1 scope (company-financial claims for US companies), lists verdict types, and distinguishes from sibling tools like compare_entities or entity_profile.

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

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

Explicitly states it replaces 4-6 sequential agent calls and implies domain via scope (company-financial). Lacks explicit when-not-to-use or alternatives, but context is sufficiently clear for the intended domain.

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