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

Beyond the annotations (destructiveHint=true, idempotentHint=true), the description explains exactly what is replaced ('in place of what the site shows now'), how the change is later superseded, and how retries are deduplicated via the same idempotencyKey. It also discloses the auth requirement (config:write). This is substantial behavioral context the structured fields do not carry.

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 sentences, each carrying distinct information: the action, the superseding behavior, the idempotency rule, and the required capability. The core effect is front-loaded with 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?

There is no output schema, so return values need not be described, and the tool is a simple 3-parameter mutation. The description covers the action, side effect, reversibility, idempotency, and permission requirement, leaving nothing an agent needs in order to call it correctly.

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%, and the schema already explains siteId (from list_sites), deployId (a 'live' deploy from list_site_deploys), and idempotencyKey retry semantics. The description's retry sentence mostly restates the schema. Baseline 3 applies since the schema does the heavy lifting.

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 specific verb and resource: 'Publish the build of an earlier deploy that went live, as a new deploy, in place of what the site shows now.' That is far more precise than the name 'rollback_site' alone and implicitly separates it from retry_site_publish and update_site. It stops short of naming a sibling explicitly, so it is clear but not fully differentiated.

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 gives clear context for when this applies: the target deploy must have gone live previously, and the effect is superseded by 'a later push to the default branch.' It also states the prerequisite 'Requires the config:write capability.' It does not explicitly say when to prefer a sibling such as retry_site_publish instead, so there is no true exclusion guidance.

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