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

Annotations already declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, so safety is partly covered. The description adds one genuinely useful behavioral rule beyond them — that modification requires the full definition plus id and current version — but says nothing about what happens on a version mismatch, whether fields are replaced or merged, or any permission requirements.

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, front-loaded statements with no filler; the create/modify purpose comes first and mode rules follow. The telegraphic style is efficient but occasionally too compressed, e.g. 'connexion IA du projet' assumes the reader knows the project context.

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 9-parameter mutating tool with zero schema descriptions and no output schema, the description covers the mode/update semantics but leaves the bulk of the payload unexplained. An agent could pick the right mode but would still be guessing about model, status and description fields.

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% across 9 parameters, so the description must compensate and it only partly does: it explains mode semantics, makes flowId conditionally required, and clarifies that id/version are needed for updates. The remaining parameters (name, instructions, model, status, description) get no meaning at all, leaving roughly half the surface undocumented.

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 gives a concrete verb pair and resource ('Créer/modifier un agent et sa mission'), which is unambiguous about what the tool does. It does not, however, contrast itself with close siblings such as run_agent, delete_agent, save_flow or save_task, so the agent must infer the boundary itself.

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 mode breakdown ('Mode workflow : flowId requis', 'Mode ai : connexion IA du projet', 'Mode external : tâches prises en charge par MCP') gives real conditional guidance for choosing between the three modes. What is missing is tool-level guidance: when to call save_agent rather than run_agent or save_flow, and whether a prior get is needed before an update.

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