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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds material detail beyond them: volumes/database data survive unless deleteData is set, and that deletion is irreversible. It does not cover required permissions or what happens to in-flight deploys.

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?

Two tight sentences with the state outcome front-loaded and the destructive caveat second. Nothing is wasted and no sentence restates the name or title.

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 mutation tool with a strong annotation set and no output schema, the description conveys the key behavioral risk (data preservation vs irreversible deletion). The remaining gap is identification: with two overlapping target parameters (name, siteId) undocumented, an agent could still be unsure what to pass.

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 only 33%; deleteData is documented in the schema and reinforced in the description, but name and siteId are undocumented in both places, and the description never clarifies how name relates to siteId (which is required to identify the target site).

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 (stops) and resource (every container service of a site), plus the resulting state change (serves static files again). It is distinguishable from delete_site, but it never names a sibling to make the boundary explicit.

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?

There is no when-to-use guidance, no exclusion of alternatives such as delete_site or abort_deploy, and no prerequisites or confirmations required. The agent must infer the usage context entirely from the action described.

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