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

Substantially exceeds the annotations: it discloses non-atomic execution with successes preserved, results keyed by index/ref, per-action validations and permissions applying, and the timeout re-run hazard. With destructiveHint and openWorldHint already declared, this adds the failure-mode context annotions cannot carry; only stopOnError behavior is left undisclosed.

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?

Dense and front-loaded: capability, prerequisite, semantics, retry warning, and side-effect caution in five short sentences. 'Envois réels uniquement si demandés' is terse but load-bearing rather than wasteful.

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 dispatcher covering ~80 action types with no output schema, it covers the essentials: non-atomicity, result addressing by index/ref, permission inheritance, and safe retry. The one material gap is the undocumented stopOnError flag and the absence of any per-action argument guidance beyond 'read 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 description coverage is 0%, so the description must compensate. It does explain the 25-item cap and the purpose of ref in results, and points the agent to per-action schemas for arguments, but the stopOnError parameter is never mentioned despite materially changing execution behavior.

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 specific verb and resource: execute up to 25 existing business actions (contacts, campaigns, courses), which distinguishes it from single-action siblings. It does not explicitly name batch_records or batch_update_pages as the alternatives, so the differentiation is scope-based rather than explicit routing.

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 real usage rules: read each action's individual schema before use, never replay an entire batch after a timeout, check business results and relaunch only the failures, and only perform real sends when explicitly requested. It stops short of saying when to prefer this over individual calls or a sibling batch tool.

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