redact_file

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

Annotations already flag destructiveHint=true and readOnlyHint=false, so the description's job is to add specifics — and it does: it discloses that redaction happens in place and overwrites the file, that a .bak backup is created by default, and that dry_run returns metrics and a preview without modification. It stops short of saying whether the token mapping is stored/reversible (relevant given reveal_text and stream_reveal_text exist as siblings) or what happens on failure mid-write.

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, front-loaded with the action and resource, then the mechanism, then the safest usage mode. No filler; the only mild redundancy is restating the backup default that no_backup already implies.

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 destructive, non-idempotent file mutation with no output schema, the description covers the essentials an agent needs to call it safely (in-place, backup, dry_run). Gaps remain around reversibility of redaction, failure/recovery behavior, and the sibling routing decision, which matter for a tool that overwrites user data.

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%, so all five parameters are already documented, and the description only echoes dry_run and the backup default. It does not resolve the profile-vs-sector aliasing ambiguity or explain the practical consequence of the free-tier character quotas listed in the schema.

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 — 'In-place redaction of a local file' — and clarifies the mechanism ('Replaces PII and secrets with tokens and saves the file'). The word 'in-place' implicitly distinguishes it from siblings like sanitize_file or sanitize_text, but it never names those alternatives, so the differentiation is left to inference.

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 one concrete usage instruction — 'Use dry_run=true to test without modifying' — which is genuinely helpful for a destructive tool. However, it never says when to pick this over sanitize_file or sanitize_text, and never states prerequisites (does the file need to be readable/writable, are large files capped by profile quota?).

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