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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds that the result is an estimate and that it 'Returns estimated score', but no precision, source of coefficients, or limitations of the estimate, so added behavioral value is modest.

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?

Purpose is front-loaded in the first sentence and the whole thing is short. The trailing 'See list_bundles for related education calculators' is the only tangential element, and it slightly dilutes focus.

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?

Output schema exists, so return-value explanation is not required, and annotations cover safety. But the description leaves two real gaps: it misstates the input signature and never distinguishes this tool from the essentially identical calculate_parcoursup_score sibling.

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 100% (bac_average, option_bonus both documented), which would justify a baseline 3, but the description actively misdescribes the inputs as 'grades and coefficients per subject' — parameters that do not exist in the schema. This is worse than staying silent and can lead an agent to expect inputs it cannot supply.

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 clear verb and resource: 'Estimate Parcoursup admission score from bac + lycée grades.' However it does not differentiate itself from the sibling calculate_parcoursup_score (or calculate_bac_points), which appear to cover the same domain, so an agent cannot tell the two apart from the description.

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 only a weak contextual cue ('Use for French university candidates') and points at list_bundles, but never states when to prefer this over the near-duplicate calculate_parcoursup_score or calculate_bac_points. Usage is implied, not specified.

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