redact

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

Annotations declare destructiveHint=false and readOnlyHint=false, so the safety profile is already covered; the description adds genuinely useful behavior beyond that by clarifying that data is truly removed rather than masked, and that sanitize=true also strips metadata, attachments and scripts. It does not discuss permissions, irreversibility of the output, or how overwrite interacts with the source file.

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 tight sentences with the core guarantee front-loaded, then parameter mapping, then the sanitize side effect. No filler, though the parameter sentences are terse enough to feel list-like.

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?

An output schema exists, so return values need no explanation, and annotations cover the safety profile. The description leaves a few gaps (overwrite semantics, only_verified meaning) but is otherwise sufficient for an agent to invoke the tool correctly.

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 0%, so the description carries the load for 7 parameters. It usefully explains kinds (find_sensitive_data categories), terms (exact names/phrases) and sanitize (strips metadata/attachments/scripts), but leaves path, output, overwrite and only_verified entirely undefined in both schema and prose.

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 effect ('Remove sensitive data for good: the characters leave the file'), and explicitly distinguishes itself from a visual overlay ('it is not a black box drawn on top'), which routes the agent away from watermark/draw-style siblings. An agent can tell what this tool does without opening the schema.

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?

The reference that `kinds` come from find_sensitive_data establishes the intended two-step workflow (find, then redact), giving clear context for when to reach for this tool. However, it never states explicit when-not conditions or names a competing alternative for destructive vs. non-destructive removal.

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