screen_candidate

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

With no annotations provided, the description explicitly marks the operation as read-only, which is a key safety trait. It also discloses that the tool aggregates and returns multiple data types (profile, resume, answers, etc.) in a single call, setting expectations for response breadth. No contradictions with annotations since none exist; however, it omits edge-case behaviors like error handling or permission 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?

Three sentences with clear front-loading: the core function first, followed by usage scenarios and parameter acquisition, then return contents. Every sentence adds value; no redundancy or filler.

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 single-parameter tool with an output schema (though not displayed), the description thoroughly specifies the return value composition. The provided workflow for obtaining application_id ensures the agent can correctly invoke the tool even without prior context. Given the tool's complexity, the description 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?

The schema already covers application_id at 100%, but the description adds crucial guidance on how to obtain the ID via a specific tool chain (search_candidates_by_name → get_candidate → match). This goes beyond the schema's bare description and helps agents understand the semantic provenance of the 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?

Clearly states it is a 'full screening package' for one candidate application, with a specific verb and resource. Distinguishes itself from sibling tools like get_candidate or read_candidate_resume by emphasizing the aggregated, one-call nature. The read-only qualifier adds clarity.

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?

Directly addresses when to use it via example user intents ('screen Sarah...' or 'give me the full picture'). Provides a step-by-step alternative workflow to obtain application_id, implicitly guiding when this tool is the right choice versus using smaller sibling tools. Explicitly mentions the integration steps leading up to invocation.

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