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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavior: the scored range is bounded at 10–990, the output includes a CEFR level plus certificate colour, and the Listening/Reading split is an estimate rather than a measured value — that last point is important framing an agent would not get from the 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?

Two sentences, zero filler, with the primary conversion mode stated first and the alternative estimation mode second. Every clause carries information (range, outputs, mode switch) and nothing is repeated from the title or schema.

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 no output schema, the description correctly compensates by naming what is returned (CEFR level, certificate colour, estimated Listening/Reading breakdown). The remaining gap is that all three parameters are optional and the description never says what happens if none are supplied or if both modes are triggered, which matters for correct invocation.

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%, so the baseline would be 3, but the description goes beyond the schema by explaining that 'score' drives one mode while the two 'bonnes_reponses_*' fields (each out of 100) drive an estimation mode. That mode-mapping and the mutual-exclusivity implied by 'Ou' is meaning the schema itself does not convey.

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 uses two specific verbs, 'Convertit' and 'estime', against a clearly named resource (score TOEIC), and spells out the exact outputs (niveau CECRL, couleur de certificat, répartition Listening/Reading). This makes it immediately distinguishable from siblings like format_toeic or guides_toeic, which do not produce a score-to-level conversion. An agent knows exactly what the tool produces without opening the schema.

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 'Ou' construction explicitly presents the two invocation modes — conversion from a total score, or estimation from per-section correct answers — which effectively tells the agent which parameters select which behavior. It stops short of stating exclusions or precedence (e.g., what happens if both modes' inputs are supplied, or when to prefer this over test_toeic_gratuit), so it is clear but not fully routed.

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