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

Goes well beyond the annotations: annotations only declare non-read-only, idempotent, non-destructive, closed-world. The description adds the actual mechanism (scale to 0 with replica count remembered), the concurrency lock semantics, the exact refusal behavior ('the refusal names the running job'), the recovery tool, and a maintenance-window refusal with a retry instruction. This is rich, actionable behavioral context.

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?

Front-loads the core action and its inverse in the first clause, then layers on constraints and recovery steps in a logical order. Dense but every sentence carries distinct operational value; the quoted maintenance message is slightly verbose but directly usable.

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 mutating operation with concurrency and maintenance-window failure modes and no output schema, the description supplies everything needed to call it correctly: effect, idempotency, lock behavior, error handling, and retry timing. Nothing material is left for the agent to infer.

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?

There is a single parameter, module_id, and schema description coverage is 100% ('Module ID (list_modules)'). The description adds no syntax or format meaning beyond what the schema already states, so the baseline of 3 for high coverage applies.

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 with the exact mechanism: 'Stop a module's pods (scale to 0), remembering how many it ran.' It further disambiguates by naming the inverse sibling unfreeze_module, so an agent can tell freeze from unfreeze and from scale_module without opening any schema.

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?

Explicitly covers when the call is a no-op ('Freezing a frozen module changes nothing'), the concurrency constraint (one operation per module, none alongside a project operation), and the alternative action when refused (wait via get_job_status, then retry). It names a sibling tool and routes the agent correctly.

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