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

Annotations already declare idempotentHint=true, readOnlyHint=false, openWorldHint=false and destructiveHint=false, so the safety profile is covered. The description adds real value by disclosing the resume behavior, which is not in annotations. It says nothing about what happens on a resumed session or what the call returns, and with no output schema the '202 + operation_status' contract lives only in the wait_s parameter description.

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 short sentences, front-loaded with the action and followed by the purpose. Almost no waste, though the trailing phrase 'you answer for the person' is unclear enough to be noise.

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 state-changing, idempotent interview-start tool with no output schema, the agent still lacks any sense of what an interview consists of, what state it returns, or how it relates to interview_answer/interview_finish. Adequate to call it, thin on surrounding 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?

Schema description coverage is 100%, so both request_key (idempotency) and wait_s (timeout with 202 fallback) are fully documented in the schema. The description contributes no additional parameter meaning, so the baseline 3 applies.

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?

States a specific verb+resource (start/resume the interview) and adds the resumption nuance, which distinguishes it from the plain 'start' siblings like start_quest. The clause 'you answer for the person' is vague and slightly muddies the purpose, and there is no explicit naming of interview_answer/interview_finish as non-alternatives.

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?

Gives a concrete reason to invoke it: it is required to open contacts. That is clear usage context. However, it does not state when to use interview_status or interview_answer instead, nor the prerequisites for resuming an existing interview.

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