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

Despite annotations, the description adds meaningful unstated context: it persists a PASS/FAIL evaluation event and flips the gate status to the verdict, which is the main side effect an agent needs to know before calling a non-readOnly, non-idempotent tool. It also discloses the return shape (verdict, per-criterion results, metrics, reason token) and enumerates the reason token values with their failure semantics.

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?

Front-loaded with the action and its effects, then the return contract and the reason-token taxonomy. It is dense — one long sentence with stacked parentheticals and a compound reason-token clause — but nearly every clause carries actionable information.

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?

No output schema exists, and the description compensates by describing the verdict, per-criterion results, metrics, and the reason token values with their interpretation. For a single-parameter mutation with side effects, nothing an agent needs to call it correctly and interpret the result 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?

Only one parameter (qualityGateId) and schema coverage is 100%, so the schema fully documents it. The description does not add format, validation, or sourcing guidance beyond 'UUID of the quality gate'; baseline 3 applies.

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+resource ('Evaluate a quality gate against current project state') and enumerates exactly what criteria are measured (test pass-rate, open critical defects, story test-coverage). This is clearly distinguishable from siblings like get_quality_gate, create_quality_gate, and update_quality_gate.

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 trailing clause gives real decision guidance: NO_CRITERIA / NO_ENABLED_CRITERIA / NO_RESULTS are described as failing closed and 'NOT a breach', directing the agent to fix the gate or run tests instead of the project. However, it never explicitly contrasts with the sibling read tool (get_quality_gate) or says when running this is preferable to simply inspecting the gate.

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