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

Annotations only cover the safety profile (readOnly=false, destructive=false), and the description goes well beyond: it discloses idempotency semantics, the rejection rule for FAIL/PARTIAL, and the 202 deferred fallback when CAPTURE_REGISTRY_ADDRESS is unset. These are exactly the runtime behaviors an agent cannot infer from structured fields.

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 compact sentences, front-loaded with the action and target, followed by the acceptance rule, then the idempotency and fallback behaviors. 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?

For a single-parameter write tool with no output schema, the description covers the success path, the rejection path, the idempotent replay case, and the not-deployed 202 case — leaving nothing material unspecified for correct invocation.

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 with 100% schema description coverage, so the schema already carries verdictId's meaning and its PASS/anchorCandidate constraint. The description reinforces but does not extend that, so the 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?

Names a specific verb (anchor) and resource (PASS capture verdict → CaptureClassRegistry), states the accepting condition (PASS + anchorCandidate) and the target chain. This is clearly distinct from sibling pcc_capture_upload (which produces the verdictId) and pcc_capture_class_registry.

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?

Gives clear preconditions: the verdict must be PASS with anchorCandidate=true, and the verdictId comes from pcc_capture_upload. It also states that FAIL/PARTIAL verdicts are rejected. It does not explicitly route the agent between this and the registry/upload siblings, but the context is unambiguous.

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