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

Goes well beyond the annotations: discloses an auth precondition (PM Career Desk account with an Interview Coach Pass), a data-handling side effect (contact details removed before recording), the return shape (compact verdict plus follow-up probe or next question), and the translation contract for non-English answers. These are exactly the traits annotations (readOnly=false, destructive=false) do not convey.

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-loads the core action and the return value, then the skip, translation and auth caveats — a sensible order with no filler sentences. The parenthetical enumeration of probe types ('own action, a result in numbers, the figure before, one specific example') makes one sentence heavy, but each clause carries information.

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?

With six parameters, no output schema and mutation-flavored annotations, the description covers the missing pieces: what comes back, what gets redacted, what identity is required, and how non-English input is handled. Nothing an agent needs to call it correctly and interpret the reply is absent.

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 coverage is 100%, so every parameter is already documented in the input schema, including lang, skip, turn, answer and text_en. The description restates the skip and translation behavior and hints at the cross-parameter rule that a literal English translation travels with the original, but adds little syntax or constraint detail the schema lacks. Baseline 3 is appropriate.

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?

Uses a specific verb pair (records the answer, checks its structure) on a specific resource (the current question of a mock interview session) and names the rule engine it delegates to (check_interview_answer). An agent can distinguish it from start_mock_interview, finish_mock_interview and check_interview_answer without reading the 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?

States the operating context (the current question or follow-up in an existing session) and the one branch condition that matters — 'skip moves on without an answer'. It does not explicitly say a session must exist first, though the session_id parameter description carries that. Clear context, but no explicit when-not/alternative routing beyond skip.

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