enforcement-database

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

No annotations provided, so description carries full burden. It discloses that the tool returns all records for the company, but does not detail output format, pagination, error handling, or authentication requirements.

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

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

Single sentence that front-loads the purpose. Slightly wordy but efficient and clear.

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

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

No output schema, but description explains the content returned (warning letters, recalls, approvals, 483s). Lacks structural details like list or pagination, but sufficient for an agent to understand what is retrieved.

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 parameter description. The tool description adds only an example slug, providing minimal extra meaning beyond the schema.

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

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

The description clearly states that the tool retrieves the full FDA enforcement history (warning letters, recalls, approvals, 483 citations) for a given company by slug. It distinguishes from siblings like get_recall_by_lot which targets a specific 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?

No explicit guidance on when to use this tool versus alternatives like search_enforcement or list_recent_actions. The description implies usage for comprehensive history but lacks when-not-to-use or alternative recommendations.

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 full burden of behavioral disclosure. It states it 'finds every FDA recall record' but fails to mention read-only nature, authentication requirements, rate limits, or error handling. The description adds minimal behavioral context beyond the obvious.

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 (12 words) that immediately conveys the tool's purpose. However, it lacks any additional useful information that could be included concisely, such as output format or behavior on not found.

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 parameter, no output schema), the description is too brief. It does not explain what the tool returns, how results are ordered, what happens if no records match, or any pagination details. This leaves the agent underinformed.

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% coverage with a description for the single parameter 'lot_number'. The tool description does not add any extra semantics or usage tips beyond what the schema provides, so baseline of 3 is appropriate.

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

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

The description clearly states the tool 'finds every FDA recall record' by 'lot number', using a specific verb and resource. It is well-distinguished from sibling tools like 'search_enforcement' which likely support broader search criteria.

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 explicit guidance on when to use this tool versus alternatives such as 'search_enforcement'. The description implies usage for lot number lookups but does not provide context, exclusions, or comparisons.

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 describes the operation as a 'direct lookup' which implies a read-only, one-to-one retrieval. However, it does not disclose behavior for invalid IDs, errors, or output format. For a simple lookup, this is acceptable but not extra informative.

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 that front-loads the purpose and example. No unnecessary words. Perfectly concise and structured.

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

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

Given the tool's simplicity (one param, no output schema, no nested objects), the description provides an example and the context of direct lookup. It could mention return type or error behavior, but is largely complete for its complexity level.

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

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

Schema description covers 100% of the parameter (wl_number) with a basic description. The description adds an example ('320-24-01'), which adds marginal value beyond the schema. No further semantics needed for a single string parameter.

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 uses specific verb 'look up', identifies resource 'warning letter', and specifies lookup by 'FDA reference/source ID' with an example. This clearly distinguishes from sibling tools like 'search_enforcement' (broad search) and 'list_recent_actions' (list).

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

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

Description explicitly states 'direct lookup', implying use when exact reference number is known. Sibling tool names suggest alternatives for history, recall by lot, recent actions, and enforcement search, but no explicit exclusion of when not to use or alternatives 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?

With no annotations, the description carries full burden. It mentions the types of items returned but fails to disclose pagination, result limits, or ordering beyond 'most recent'. The parameter 'days' is described in the schema but not in the text.

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 of 16 words with no superfluous information. It is front-loaded with the main purpose. However, it could be slightly more concise by removing 'across all streams' 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 no output schema and moderate complexity, the description should explain return structure (e.g., list of objects with fields). It does not mention pagination, count limits, or response format, leaving gaps for an agent.

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

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

Schema coverage is 100% with one well-described parameter (days). The description adds no extra meaning about parameters beyond what the schema provides, so baseline score of 3 is appropriate.

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

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

The description clearly states the tool lists recent FDA enforcement actions (warning letters, recalls, approvals, 483s) across all streams. The verb 'list' and resource 'recent FDA enforcement actions' are specific, and it distinguishes from siblings like get_recall_by_lot or get_warning_letter which target specific subsets.

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 a broad overview of recent actions but does not explicitly state when to use it versus alternatives like search_enforcement or get_company_history. No exclusions or when-not guidance 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?

With no annotations, the description must disclose behavioral traits. It mentions the search scope and categories but does not state that the operation is read-only, whether authentication is needed, rate limits, pagination, or result limits. This is a significant gap for a search 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 concise, using two sentences with no redundant words. The first sentence fronts the core purpose. It could be slightly clearer about the distinction from sibling tools, but overall it is 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?

For a simple search tool with one parameter and no output schema, the description adequately explains what is searched (over 1,000 pages, specific categories) but does not describe the output format (e.g., list of results, metadata). This is a moderate omission.

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 'query' parameter, and the description repeats the schema's note that it supports company names, product names, or keywords. No additional meaning is added beyond the schema, so baseline 3 is appropriate.

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

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

The description clearly states the tool performs a 'full-text search' across over 1,000 FDA enforcement pages, listing specific categories (warning letters, recalls, approvals, 483 inspections). This distinguishes it from sibling tools that target individual records by lot, company, or specific actions.

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

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

The description implies the tool is for broad keyword searches across all enforcement pages, but it does not explicitly state when to use this tool versus alternatives like get_company_history or get_recall_by_lot. No when-not criteria are provided.

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