health-intel

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

With no annotations provided, the description bears full responsibility for behavioral disclosure. It only states that the tool returns 'recent' actions, but does not specify recency limits, output format, pagination, or any side effects. This is insufficient for an agent to fully understand the tool's 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?

The description is extremely concise—one sentence plus a parenthetical—with no wasted words. Every part serves a purpose, making it easy for an agent to parse quickly.

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 (single parameter, no output schema, no annotations), the description provides sufficient information to understand its purpose and target audience. It is complete for a tool of this complexity.

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

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

The sole parameter 'firm' is adequately described in the schema ('Recalling firm / manufacturer name.'). Since schema description coverage is 100%, the description adds no additional meaning beyond what the schema provides, warranting a baseline score of 3.

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

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

The description clearly specifies the verb 'Return', the resource 'FDA enforcement/recall actions', and the scope 'tied to a device/drug firm'. It distinguishes itself from siblings by focusing on FDA enforcement, while siblings like 'provider_lookup' and 'new_exclusions' suggest different domains.

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

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

The description mentions the tool's context for procurement and payor teams, implying when it might be used. However, it does not explicitly state when to use this tool versus alternatives, nor does it provide exclusions or prerequisites.

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 but only notes the tool returns providers and can be scoped. It does not explain what 'newly added' means (time frame), pagination behavior beyond a default limit, or any side effects or auth requirements. This leaves critical behavioral 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 two sentences with key information front-loaded. It is efficient with no redundant phrases, though a bit more context on parameters could be added without significant bloat.

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

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

Given the tool has 3 parameters, no output schema, and no annotations, the description is incomplete. It does not explain the return format, how 'newly added' is determined, or how the limit parameter affects results. This leaves the agent with significant uncertainty for invocation.

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

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

Schema coverage is only 33% (only limit has a description). The description adds that state and specialty are optional scoping filters, but provides no format details (e.g., state codes, specialty names) or constraints. This minimally compensates for the schema gaps but is insufficient for effective parameter usage.

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

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

The description clearly states the tool returns providers newly added to the OIG-LEIE exclusion list, with optional scoping by state and/or specialty. This specific verb-resource combination distinguishes it from sibling tools like screen_exclusion, which likely checks for current exclusions rather than new additions.

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 identifies the tool as a 'credentialing / payment-integrity alert feed,' implying use for monitoring new exclusions. However, it does not explicitly state when to use this tool versus alternatives like screening, nor does it mention prerequisites or when not to use it.

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

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

Given no annotations, the description carries the full burden. It discloses the data source (public, no PHI), returned fields, and the OIG-LEIE exclusion flag. However, it does not explain behavior when both npi and other parameters are provided, or how default limit applies, which are minor 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?

Three sentences, no wasted words. Front-loaded with the primary action and quickly enumerates inputs and outputs. 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?

With 6 parameters, no output schema, and no annotations, the description is largely complete: it covers purpose, inputs, and output fields. It omits details like error handling or pagination, but for a lookup tool the provided context is sufficient for most use cases.

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

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

Schema description coverage is 83%, so the baseline is 3. The description adds value by clarifying the two usage modes (by NPI vs. by specialty+state with optional fields), which the schema alone does not convey. This extra context raises the score.

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 looks up US healthcare providers from the CMS NPPES registry, specifying two search modes (by NPI or by specialty+state with optional name/city) and lists returned fields. This distinguishes it from siblings like fda_enforcement and screen_exclusion.

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 how to use the tool (two modes) but does not explicitly state when to use this tool versus alternatives like new_exclusions or fda_enforcement. The phrase 'Public data only — no PHI' provides a constraint but no comparative guidance.

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

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

With no annotations, the description carries full burden and excels: it discloses exact vs flagged matching, identity-cautious handling, return type (sourced findings + disclaimer), and a factual tone. No contradictions.

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

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

Two sentences, no redundancy, front-loaded with key action. Every phrase adds value. Perfect conciseness.

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

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

Given no output schema and no annotations, the description explains purpose and matching but omits the 'state' parameter's role and output structure details. Adequate for a simple tool, but gaps remain.

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

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

Schema coverage is 0%, so the description must compensate. It explains the behavior of npi (exact match) and name (flagged), but does not mention the 'state' parameter at all. Partial coverage only.

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 ('Screen a provider/organization'), specifies the target lists (HHS-OIG LEIE, SAM.gov), and explains matching types. It distinguishes from siblings like fda_enforcement and provider_lookup which have different scopes.

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

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

The description does not provide explicit guidance on when to use this tool versus alternatives, nor does it mention prerequisites or context. While the purpose is clear, the lack of when-not-to-use or sibling differentiation prevents a higher score.

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