Qu'est-ce qui demande mon attention aujourd'hui ?

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

Annotations already mark it readOnly and idempotent; the description adds that it makes no BoondManager API calls, reads no data, and generates the response server-side. However, the first sentence says it reads alert indicators and executes searches, directly contradicting the later clarification. This internal contradiction muddies the behavioral expectations despite the additional disclosure.

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 structured into 'Quand', 'Plutôt que', and 'Returns' sections, which aids readability. However, it is somewhat verbose, and the misleading opening sentence adds noise. The clarification that no API is called appears twice, which 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 tool with no parameters and no output schema, the description explains the return format (a text runbook with ordered calls and exact filters), the fact that the model must execute the calls, and the absence of API calls or data reads. This is sufficient for an agent to call the tool correctly and know what to do with the result.

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?

The input schema has zero parameters and schema coverage is 100% trivially. With no parameters, the description does not need to explain parameter meaning, and it appropriately doesn't. The baseline for zero parameters is 4, and the description provides no conflicting guidance.

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 that the tool returns a text runbook listing the ordered Boond calls to execute, with exact filters, for the 'attention due today' scenario. The opening sentence describes a sequence of reading indicators and executing searches, but the Returns section clarifies that the tool actually generates instructions rather than performing those actions. It does not explicitly compare to sibling workflow tools, but the scenario is distinct enough.

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 'Quand' section explicitly says to use it to execute a multi-step scenario without having to find the right tool chain and filter names. The 'Plutôt que' section names an alternative MCP prompt and specifies when to prefer this tool (when prompts/get is poorly handled, e.g., claude.ai). It also states that no API is called and that the model must execute the returned runbook, defining the expected usage pattern.

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