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

Annotations cover safety (readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=true). The description adds genuinely non-structured behavior: an explicit user-confirmation gate before invoking an external service. It does not mention cost, latency, or failure behavior, keeping it below a 5.

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 short sentences, no padding, with the action and the precondition front-loaded and the parameter requirement last. Every sentence carries required 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?

There is no output schema, but the description does not need to describe return values since it covers the call preconditions and input contract fully. Minor gap: nothing about what happens on rejection or how results are surfaced.

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 100%, so the baseline is 3. The description adds meaning beyond the schema by specifying the either/or requirement between job_id and map_id and flagging anonymized_text as the fallback path, which the flat schema does not express.

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: send anonymized text or a completed file job to Claude Legal. The 'already-anonymized' and 'completed file job' qualifiers implicitly separate it from anonymize_document and redact_pii, though no sibling is named directly.

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 a clear precondition chain: call only after the user has previewed the anonymized content and confirmed. It also states the required inputs (confirmed=true plus job_id or map_id). No explicit exclusion or named alternative, but the sequencing relative to the anonymize step is unambiguous.

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