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

Annotations only supply destructiveHint=true; the description earns credit by disclosing the async 202 contract, the operation-tracking path, and the partial-application semantics. It does not warn that reducing amount (especially to 0) removes running containers — a material destructive consequence for a tool flagged destructive.

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?

Three tight sentences, front-loaded with the mutation warning and effect, then partial-update rule, then return/endpoint mechanics. No filler.

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 two-parameter write tool with no output schema, the description covers effect, scope, and async return handling adequately. Minor gaps: what happens at amount 0, and any size/plan constraints, are left unstated.

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%, so app/containers/name/size/amount are all already documented in the schema; baseline is 3. The 'only included types are changed' sentence adds genuine meaning about how the containers array is interpreted (omission ≠ removal), but no additional per-field detail beyond that.

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: 'sets the container formation (number and/or size of each process type)'. The 'MUTATES' prefix and container-formation framing cleanly separate it from the read-only sibling scalingo_list_containers, and it names the exact API endpoint.

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 partial-update rule ('Only the container types you include are changed') tells the agent this is a targeted patch rather than a full replace, and it explicitly routes follow-up polling to scalingo_get_operation. It stops short of stating when NOT to use it (e.g., use scalingo_restart_app for restarts without resizing).

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