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

Annotations already declare this is a non-read-only, non-destructive, non-idempotent mutation, but the description adds material context the annotations cannot: the original text is retained and the operation is reversible via revert_knowledge_redaction. That is exactly the reassurance an agent needs before invoking a content-modifying tool. It stops short of describing permissions or what happens to non-listed findings.

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?

Two tight clauses with the core action front-loaded before the parameter explanation and the reversibility caveat. No filler sentences. Minor ambiguity in 'finding ids to replace' — the replacement value is never stated, only implied as a redaction.

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 mutation with three required params including a nested object and no output schema, the description covers the action, the key parameter shape, and the undo path. It leaves open edge cases (empty approved map, partial application failures) but nothing that would prevent a correct call.

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 coverage is 75%, and the one undocumented parameter is the complex nested one: the description explicitly explains that 'approved' is a map of document id to finding ids to replace, which is genuinely additive over the bare additionalProperties schema. The remaining parameters are already described in the schema, so no further compensation is required.

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 and resource ('Redact the chosen findings of a scan') and distinguishes itself from the read-only discovery sibling by naming the scan as its input source. An agent can tell it apart from scan_knowledge_for_sensitive_data and revert_knowledge_redaction, though it never explicitly names the scan tool itself.

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?

Usage is implied rather than stated: the reader infers it runs after a scan and that revert_knowledge_redaction is the counter-operation. There is no explicit when-to-use/when-not-to-use guidance, and it does not distinguish itself from set_knowledge_redaction_policy or the other redaction siblings.

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