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

Annotations already declare readOnlyHint=true, so the safety profile is covered. The description adds useful behavioral context: it reports live CPU/mem vs plan caps, deploy history, and plan/per-project caps in the rollup. It doesn't mention pagination or exact response shape, but for a read-only stats tool this is sufficient.

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 sentences, all informative, with the most important scoping behavior front-loaded. No filler or repetition of schema details.

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 read-only stats tool with one optional parameter and no output schema, the description covers the key decision (project vs account-wide), the data reported, and the plan caps. It doesn't describe the exact response structure, but that's not required given the absence of an output schema and the tool's simple scope.

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 0% and the schema only says `project` is a string. The description compensates by explaining that `project` can be a project id or slug, and that omitting it returns account-wide stats. This adds meaning beyond the schema, though it doesn't specify format constraints (e.g., slug pattern).

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 a specific verb ('get') and resource ('stats'), and clearly distinguishes between account-wide and per-project stats. It also names the plan caps and deploy history, which makes the tool's purpose concrete and distinct from siblings like get_status or get_logs.

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 description explicitly explains when to omit `project` (all of the caller's projects) and when to pass a project id or slug (single project). It also clarifies that the account rollup reports plan and per-project caps, giving the agent clear selection criteria without needing to inspect the schema.

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