render_image

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

Goes well beyond the annotations: async non-blocking behavior, immediate job_id return, the caveat that max_time_s is indicative and scene prep adds overhead with a concrete 10s→80s example at 2560×2560, and the single-render-at-a-time limit. This is exactly the kind of behavioral context annotations cannot carry.

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?

Dense and front-loaded: purpose and async contract come first, then parameter notes, then the wait_for_render handoff and the material-change warning. Nearly every sentence earns its place, though the parameter notes are compressed into a run-on block.

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 an output schema present, the description needn't explain the return beyond noting job_id, and it covers the critical async/caveat behavior. The remaining gap is the undocumented overwrite and max_samples parameters, which matter for a tool that writes files.

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 0%, so the description must compensate. It does well for path (absolute, accepted extensions, default output folder), width/height (defaults to scene render resolution), and max_time_s (indicative semantics), but leaves overwrite and max_samples completely unexplained.

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+resource ('Lance un rendu') and immediately clarifies it is always asynchronous and returns a job_id right away. This distinguishes it cleanly from wait_for_render, render_status, and screenshot, which are adjacent siblings.

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?

Gives explicit routing ('Puis wait_for_render'), a hard concurrency constraint ('Un seul rendu à la fois'), and a usage prohibition ('Ne pas changer de matériau pendant un rendu'). The agent knows both what to do after and what not to do during.

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