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

Annotations only declare the read-only safety profile; the description adds substantial beyond-schema behavior: an AI-drafted portion via named models with a backup, the ATSPrep guard that strips figures/names/tools absent from the user's text, and graceful degradation to a rule-based result with ai.message explaining unavailability. It even implicitly explains the non-idempotent hint via model variability.

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?

Purpose is front-loaded in the first clause and the output list is dense but informative. The middle sentence's model/infrastructure detail (Gemma 4, Llama 3.3 70B, Cloudflare Workers AI) is more implementation depth than an agent needs to select the tool, making it slightly top-heavy.

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 no output schema, the description must carry the return-value burden and does: it enumerates the review components and explains the degraded-mode response plus the ai.message field. Nothing an agent needs to call this 4-parameter tool correctly is missing.

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 the schema already documents all four parameters, including the kind enum's five modes and length limits. The description adds no parameter-level detail beyond what the schema provides, which sets the baseline at 3.

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 ('Review the user's answer to an interview question') and enumerates the concrete artifacts produced (rating, speaking time, STAR coverage, filler words, follow-up, stronger version). This is clearly distinct from the sibling interview_questions, which generates rather than critiques answers.

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?

Usage is implied by the function rather than stated: there is no explicit 'use this when you have a drafted answer and want feedback' or mention of alternatives like interview_questions. The kind enum in the schema carries the closest thing to usage routing, and the description itself offers no exclusions or prerequisites.

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