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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered structurally. The description adds value beyond that by disclosing the shape of the payload (transcript restricted to speaker turns only; evaluation broken into score, performance, per-question, summary, pros/flags), which tells the agent what it can and cannot extract. It does not say what happens when no AI interview exists for the pair.

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, front-loaded with the core action and immediately followed by the return payload and the scope exclusion. No filler, no restatement of the title, and every clause contributes either identification or expectation-setting.

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 exists, so the description rightly shoulders the burden of describing return values, and it does so at a useful granularity. The remaining gap is failure/empty-state behavior — what a caller sees when the candidate has no AI screening interview — which matters for a two-required-ID lookup tool.

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%, with both required parameters documented as candidate ID and job position ID, so the schema already carries the semantics. The description adds only the framing that the two IDs jointly identify the interview, without clarifying pairing rules, mismatch behavior, or whether the candidate must be in the job's pipeline. 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 and resource ("Get the result of a candidate's AI screening interview for a job position") and then enumerates exactly what the result contains: transcript speaker turns plus AI evaluation with overall score, per-question evaluations, summary, pros and flags. It also carves out a scope boundary ("Interviews held with a person are not included"), which separates it from transcript/report siblings.

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 clear condition of applicability by scoping to AI screening interviews and excluding human-led interviews, which is the key decision an agent faces in this crowded sibling set. It stops short of naming the alternative tool to use for human interviews (e.g. get_meeting_report or get_meeting_transcript), leaving that routing to inference.

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