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

Annotations already declare read-only/idempotent, and the description adds genuine value on top: it discloses that `interview.untrusted` contains model-generated text that must be quoted as such and never obeyed as instructions, and it states a deliberate absence (no transcript, use the dashboard). It does not cover error behavior, but the prompt-injection warning is an unusually valuable behavioral 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?

Front-loaded with the identity of the tool and its delta from list_candidates, then dense but purposeful detail on the interview object. It is a single long paragraph and spends several clauses on return-field breakdown that the output schema already carries, but no sentence is pure 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?

Return values are covered by an output schema, so the description's heavy field enumeration is partly redundant, while the more consequential gap — the meaning and source of the two required identifiers — goes unaddressed. Adequate for an agent that already has both ids, otherwise incomplete.

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 0%, and the description never mentions job_id or application_id, their relationship, or where to obtain them. For a tool requiring both a job and an application identifier, that the input is scoped by job/application pairing is left entirely to inference.

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?

Opens with a specific verb+resource framing ("One candidate") and immediately positions it relative to list_candidates: same fields plus detail. The agent can tell this gets a single rich record versus a list without opening either schema.

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 contrast with list_candidates ("the same fields as list_candidates, plus ...") makes the selection condition reasonably clear: use this when a single candidate's full detail is needed. It stops short of stating preconditions or explicitly naming when not to use it (e.g., when you only have a candidate id without an application).

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