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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it delivers: it reveals that generation is asynchronous, that the request is idempotent, that failed exports are retried at no charge, and that the final artifact is downloaded from the web app rather than returned by this tool. These are exactly the behavioral traits an agent needs to know before invoking and after invoking.

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?

Every sentence earns its place: the first defines the exact deliverable, the second covers plan/billing eligibility, and the third covers lifecycle, idempotence, and retry policy. The most critical information is front-loaded, and there is no filler or repetition of schema fields.

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 single-parameter tool with an output schema already present, the description covers every contextual angle that matters: eligibility, billing, async behavior, polling target, download location, idempotence, and failure handling. The caller has everything needed to correctly select and invoke the tool without guessing.

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 0%, so the description must compensate for the single parameter, verification_id. While it does not spell out 'verification_id is the ID of your verification', the phrase 'for a completed RAW+JPEG verification you own' functionally explains what the identifier refers to and implies the required ownership and completion constraints. A slightly more explicit mapping to the parameter name would push this to a 5.

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?

The description states a specific verb ('Request'), a concrete resource ('a layered flicker-comparison PSD for a completed RAW+JPEG verification'), and exactly what the export contains (original photo, RAW rendition, SSIM heatmap). It also differentiates from sibling tools by naming get_psd_export_status as the polling endpoint. No ambiguity remains about what the tool does.

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 description gives explicit eligibility conditions: the verification must be completed, must be RAW+JPEG, and must be owned by the caller. It also states the Professional-plan restriction and the metered billing model. It tells the agent to poll get_psd_export_status until 'completed' and then download from the verification page, which clearly routes the caller through the async lifecycle. This is as explicit as a caller could reasonably need.

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