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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false, and openWorldHint=false. The description adds the meaningful behavioral trait that the tool blocks unsafe material rather than passing it through, but says nothing about failure/rejection semantics, what happens on success, or whether the payload is forwarded automatically.

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?

A single well-formed sentence with no filler and the action front-loaded. It is efficient, though borderline terse for a tool whose failure behavior matters.

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-param, mutation-flagged tool with no output schema, the definition is minimally adequate. It omits what a caller needs to know about the rejection response and forwarding behavior, leaving gaps beyond what the annotations cover.

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 exists and its schema description has 100% coverage, so the baseline is 3. The description adds no syntax, format, or content detail about the body beyond what the schema already says (deferring to the OpenAPI contract).

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 pair (check/reject) and resource (payload PII) with a clear scope of operation ('before forwarding'). It is clear what the tool does, though it does not distinguish itself from sibling gate/check tools such as edge_audit or the various *_check tools.

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?

'Before forwarding it' implies the usage context (an outbound/inline gate), but no alternatives are named and no conditions for when-not to use it are given. Usage is inferable rather than explicit.

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