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

Annotations already cover the read-only and non-destructive nature (readOnlyHint=true, destructiveHint=false), so the description correctly adds interaction details: it returns questions when information is missing, and Elo/plateforme replaces other questions. This goes beyond the annotations and helps the agent predict the tool's response pattern, though it doesn't describe the output format in detail.

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 a bit long but each sentence serves a distinct purpose: purpose, usage trigger, minimal info, Elo alternative, and missing-info behavior. It is front-loaded with the core purpose and avoids redundant statements, though some phrasing could be tightened.

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 6-parameter tool with only 1 required, the description covers the essential usage logic: when to call, what info is needed, and what to do when info is missing. It doesn't explain the output format, but with no output schema and given the tool's interactive nature (returning questions), this is acceptable. The sibling context is clear, and the description fills gaps left by the schema.

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% with each parameter described individually. The description adds semantic context by identifying which three parameters are sufficient (depuis_quand, age, demande) and clarifying that Elo and plateforme replace the others. This relationship is not in the schema, adding real value for selecting and filling parameters correctly.

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 clearly states the tool's purpose: to recommend one specific offer based on the person's profile using the APP24 method. It explicitly differentiates from siblings by saying 'plutot que de chercher dans le catalogue et de choisir toi-meme', so an agent knows it is not a search tool but a personalized recommendation engine.

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 gives explicit triggers: 'A appeler en priorite des que quelqu'un demande par ou commencer, quoi acheter, quoi offrir, ou comment progresser'. It also tells the agent not to use catalog search as an alternative and explains how to handle missing information (ask questions back). This is highly actionable and leaves no ambiguity about when to use the tool.

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