Voir le dessin

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

Beyond the readOnly/idempotent/non-destructive annotations, it discloses framing behavior (auto-centered on content), an edge case (empty drawing yields an empty image, not an error), and a backend constraint (needs a render-capable engine; DXF yes, AutoCAD no). This is substantial context the annotations do not 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?

Front-loaded with the operation, then the usage directives, then runtime caveats. Four short paragraphs are all relevant, though the 'sans regarder, vous dessinez à l'aveugle' line is rhetorical padding rather than information.

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 render tool with no output schema, the description covers what is returned, how the image is framed, the empty-drawing edge case, and backend prerequisites. An agent has everything needed 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?

Schema description coverage is 100% and both width/height are documented with defaults and bounds in the schema, so the description adds no parameter detail. Per the rubric, baseline 3 applies when the schema does the heavy lifting.

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 and resource ('Rend le dessin courant en image PNG') plus the returned payload (image, entity count, drawing bounds). It implicitly separates itself from query/info siblings by positioning the render as the way to see what was actually drawn.

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?

It gives explicit triggers: call after every write batch, and before correcting an existing drawing. The rationale ('only way to verify what was actually traced instead of trusting a report') makes the when/when-not condition unambiguous.

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