Propose redaction rules

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

Annotations declare readOnlyHint=false, idempotentHint=true, destructiveHint=false, but the description adds the key underlying reason: 'Scanning records each suggestion in the engine,' which explains the non-read-only hint as a benign recording side effect rather than mutation. It also discloses the out-of-band install path, which the structured fields cannot convey.

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?

Purpose and scope are front-loaded in the first sentence, with the side effect and installation workflow following. The second and third sentences are dense but each carries real information; 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, but the description specifies the return ('only the redaction-kind suggestions') and the recording side effect, plus the install follow-up path. An agent has enough to call it and understand consequences, though return-shape specifics are minimal.

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 100% and the single `limit` parameter is fully documented in the schema (including its server-side default). The description adds no parameter detail, so the baseline of 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?

The description states a specific verb+resource (scan captured traffic for PII/secret patterns, propose redaction rules) and scopes the output precisely: only redaction-kind suggestions not already covered by existing rules. This cleanly separates it from siblings like list_findings or rescan_findings.

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?

It explains the intended workflow and, critically, that installing a suggested rule is NOT exposed over MCP, naming two alternatives (accept in the app's suggestions view, or `proxykit redaction add --path <key>`). It does not explicitly state when to call this versus rescan_findings or list_findings, so it falls short of full when/when-not coverage.

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