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

Annotations cover read-only and safety, but the description adds crucial behavior: default minScore 90 with no criteria, no-scan and unfinished-scan both fail, page coverage is reported, and the tool judges the record only. It also names the enterprise plan requirement. These details go well beyond annotations and materially affect correct invocation.

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?

The description is dense but front-loaded, starting with the core purpose and moving through criteria, failure semantics, coverage, and scope. Every sentence earns its place, though the single paragraph could be slightly more scannable with minor formatting. It is appropriately sized for a complex gate tool.

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?

Given the 4-parameter schema, no output schema, and CI-gating complexity, the description covers everything an agent needs: defaults, combined criteria, failure as a normal result, no-scan failure, unfinished-scan failure, page coverage, and the fact that no scanning occurs. Nothing critical is missing.

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 description coverage is already 100%, so baseline is 3. The description adds useful interpretation: criteria can be combined, default minScore 90 applies only when no criterion is given, and maxSerious is explained as the high-severity tier axe calls serious. That is meaningful clarification beyond the schema text.

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 and outcome: turning the last recorded scan into a passed true/false verdict against thresholds. It clearly scopes the tool to CI/deployment gating, distinguishing it from sibling tools that scan, list violations, or report status. An agent can immediately tell this is a gate, not a scanner.

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 says to use it in CI or a deployment pipeline when a build should be blocked or allowed, and clarifies that no page is loaded or scanned by calling it. It also warns that a failing verdict is a normal result, not an error, so the agent knows not to retry. This is exactly the when/how guidance an agent needs.

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