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

Even with readOnlyHint and openWorldHint annotations already covering safety, the description adds crucial behavioral detail: signed URLs expire after an hour, files persist until expires_at, past expiry returns retention_expired with 410 and render/template version, and it is free and never re-renders. No contradiction with annotations.

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 description is front-loaded with the core action and then packs important behavioral details into a compact, well-structured paragraph. Every sentence adds relevant operational context without redundancy.

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?

Given the tool has only one parameterhare no output schema, the description fully covers return values, statuses, error conditions, expiry semantics, and cost/no-render behavior. An agent has everything needed to decide when and how to call it correctly.

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?

The schema already covers 100% of the single parameter with a clear description and example. The tool description confirms the render_id comes from a previous render call but adds little beyond the schema, so the baseline of 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?

Description clearly states it fetches a render by id, returning status and a signed URL. It differentiates itself from siblings like 'render' and 'list_renders' by emphasizing polling and re-signing, so an agent knows exactly what this 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?

Explicit use cases are given: poll a queued render or re-sign an expired URL. It also explains the expiry behavior and that the tool never re-renders, implying when to avoid it, though it doesn't explicitly name an alternative like 'render' for re-rendering.

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