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

Annotations already declare destructiveHint=true, idempotentHint=true, readOnlyHint=false and openWorldHint=false, so the safety profile is largely covered structurally. The description adds scope-limiting context ('does not schedule interviews or send email') and the review precondition, but says nothing about reversibility (an undo sibling exists) or required permissions.

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, front-loaded sentences with no filler; the core action comes first and the scope limitation second. It is efficient, though arguably too terse given the surrounding gaps.

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 destructive mutation in a dense sibling set (undo_candidate_admission, decide, transition_direct/bind/preview), the description covers the core action and one negative boundary but omits preconditions of 'reviewed', the reversal path, and any parameter meaning. Adequate but with clear gaps.

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?

Three parameters with 0% schema description coverage: application_id is only obliquely implied by 'one reviewed application', and request_id and idempotency_key are completely unexplained. Given that idempotency_key semantics (safe retry) are operationally important for a mutation, the description fails to compensate for the coverage gap.

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 ('Move one reviewed application to Candidates'), which clearly distinguishes it as a stage-transition mutation rather than a read or create. However, it never names its closest siblings (yardstick_applications_undo_candidate_admission, yardstick_applications_decide, the transition_* family), so an agent must infer the boundary from the name alone.

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 phrase 'one reviewed application' implies a precondition (the application must already be reviewed) and the trailing sentence rules out adjacent behaviors (interview scheduling, email), which narrows usage somewhat. But there is no explicit when-to-use statement or routing to alternatives such as undo_candidate_admission for reversal.

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