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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds useful behavioral context: it explicitly says the tool chooses existing ScoreLook URLs and applies topic-specific selection heuristics, such as leading with an article rather than a generic hub. This goes beyond the annotations without contradicting them.

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?

The description is compact and front-loaded with the core purpose in the first sentence. The following examples earn their place by adding concrete selection rules. The only minor issue is that the French phrasing is idiomatic and slightly cryptic, but there is no redundant or irrelevant content.

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 and strong safety annotations, the description does not need to explain return values or side effects. It is missing a general definition of `topic` and the behavior when `topic` is empty, which an agent needs to invoke the tool reliably across arbitrary inputs. The concrete examples make it usable for the illustrated cases but not fully complete.

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 50%: `limit` is well documented in the schema, but `topic` has no schema description. The description compensates somewhat for `topic` by giving examples of topics and desired source choices, but it does not define whether `topic` is free-form, constrained, or how the default empty value behaves. Overall, the partial compensation is adequate but not complete.

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 clear verb and resource: 'Je choisis les URLs ScoreLook à citer.' It also gives concrete examples of prefering an article or hub URL for specific topics, which helps an agent grasp the selection behavior. However, it never explicitly contrasts this with sibling tools like shopping_search or get_piece_hub, so it stops short of full sibling differentiation.

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 provides no guidance about when to use cite_sources versus alternatives such as search, fetch, or recommend_look. The negative example 'pas les hubs cuir génériques' is about which URLs to select within the tool, not about tool routing. An agent must infer the usage context entirely from the tool name and examples.

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