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

Annotations already declare readOnlyHint=false, idempotentHint=true, and destructiveHint=true, so the bar is lower. The description adds one useful behavioral fact: despite being a mutation, it does not change application status. It does not disclose broader side effects, such as whether the recommendation overwrites prior evidence or affects downstream decision processes.

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 one short sentence split into two clauses. It front-loads the action and resource, then adds a scoping clarification. Every word contributes; there is no filler or repetition of the tool name.

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 seven parameters, no output schema, a destructiveHint=true annotation, and a large sibling set, this description is too thin. It gives no guidance on expected outcome, return value, rating scale semantics, idempotency behavior beyond the annotation, or how this tool fits into the hiring workflow. A capable agent could call it, but would be guessing at workflow 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 0%, so the description carries the burden of explaining parameters. It adds no meaning for application_id, interviewer_user_id, rating, notes, request_id, session_id, or idempotency_key. The schema property names are somewhat self-explanatory, and rating has min/max, but the description does not clarify semantics such as what 'rating' represents or which identifiers are required.

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 uses a specific verb ('Record') and resource ('direct final-recommendation evidence'), and adds a scope qualifier ('does not mutate application status') that distinguishes it from transition/bind siblings. It is slightly jargon-heavy ('direct...evidence'), but the core action is clear.

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 clearly implies this tool is for recording final recommendation evidence, and the 'does not mutate application status' clause provides a useful boundary against status-changing tools. However, it does not explicitly state when to prefer this over related tools like decision bind/preview or scorecard submission, nor does it name alternatives.

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