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

Adds substantial context beyond the annotations: the operation is non-destructive to the original (a new photo is produced), it consumes credits, and there is no charge when no faces are detected. It also explains the non-idempotency implied by idempotentHint=false by warning that a silent call may already have started. It does not say what is returned (e.g. new photo id) or how quickly the result appears, leaving a small gap.

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-loaded with the core action and cost, then alternates, then parameter guidance, then the retry warning — a sensible order with no filler. The opening sentence is long and stacks several clauses, slightly hurting scannability.

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, credit-consuming mutation with no output schema, the description covers cost, no-face behavior, app-based alternative, and the retry hazard. What is missing is the return value and whether/how the caller learns the new photo's id, which matters for chaining into list_photos or edit.

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?

With 0% schema description coverage, the description carries the burden and mostly does: it explains the effect values (blur/pixelate), the strength scale semantics (0 light to 100 strong), and critically where max_credits comes from ("the photo's prices from get_shoot or list_photos"). photo_id is only implied by "one of the user's photos," and the strength default of 70 is not mentioned.

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 ("Hides every face in one of the user's photos"), plus the outcome ("as a new photo") and the cost model ("paid from their credits"). No sibling tool (edit, upscale, zoom_in, reroll, etc.) does this, and the description makes the distinction obvious without opening any 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?

Explicitly routes the agent away from this tool when per-face control is needed: "To keep some faces sharp or hide one it missed, the user opens the photo's link and uses Blur faces in the app." It also names prerequisites (price from get_shoot or list_photos) and a retry protocol (check list_photos before calling again after a non-answer).

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