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

No annotations exist, so the description carries the full burden and does so well: it discloses the dry-run-by-default behavior, the commit gate that makes the call actually write, the downstream blocking effects, and the ethical constraint that this is a statement to a regulator rather than an inferable fact. That is exactly the context an agent cannot get from structured fields.

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 dry-run warning and the regulatory framing are front-loaded, and every clause conveys actionable information. The middle sentence is long and stacks three separate failure consequences, which could be tightened, but nothing is filler.

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 six-parameter mutation tool with no annotations and no output schema, the description supplies motivation, failure modes, safety posture, and even what the dry run returns (a list of assets it would mark). Nothing an agent needs to invoke it 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 coverage is 100%, so all six parameters are already documented, which sets the baseline at 3. The description adds real value on top by emphasizing DRY-RUN BY DEFAULT (the commit parameter's most dangerous misfire mode) and by framing ai_declaration as a fact to confirm with the user rather than deduce.

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 (declare) and a precise, narrow resource (whether the store listing's images were AI-created/edited), which is unmistakable against siblings like update_content_rating or update_data_safety. The scope — a regulatory declaration attached to the listing's images — is spelled out rather than implied.

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 tells the agent when this is mandatory (required Review step), what breaks without it (listing stays Draft, store_listings task incomplete, send_app_for_review returns FAILED_PRECONDITION), and how to source the value (ask the user, never infer). It also names the dry-run default up front so the agent knows the initial call is non-committal.

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