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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuine behavioral context beyond that: no processing happens by default, no duplicate image is produced when no correction is useful, and lost detail in very blurry photos is not reconstructed. These are non-obvious expectations about the returned data that an agent would otherwise have to guess.

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?

Four short sentences, with the core purpose stated first and the caveats (no default enhancement, no duplication, no detail reconstruction) following in decreasing order of importance. No filler; each sentence carries a distinct constraint.

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 single-parameter read-only tool with no output schema, the description does the heavy lifting: it says conceptually what is returned (original and enhanced versions plus the corrections applied) and sets expectations about when no enhanced version exists. The only meaningful omission is what assetId refers to.

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?

There is one required parameter (assetId) with 0% schema description coverage, so the description must carry the meaning — but it only says "d'une image du projet" without explaining what identifier assetId is, where it comes from, or how to obtain it. With only one parameter the baseline is 4, but the complete absence of parameter guidance here leaves a real gap.

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?

"Lire les versions originale et améliorée d'une image du projet et les corrections effectuées" gives a specific verb (read) and a precise resource (the original + enhanced versions and the edits applied). It implicitly distinguishes itself from the enhancement path by naming enhance_image, though it never explicitly contrasts with select_image_version, which is the closest sibling.

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 description states a when-not rule for processing ("Aucun traitement par défaut : enhance_image ou enhance:true à l'import uniquement sur demande explicite de l'utilisateur") and names enhance_image as the alternative for actual enhancement. However, it never says plainly when an agent should call this tool (e.g. before choosing a version with select_image_version), so the usage context is only implied.

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