Redact a local file

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, yet the description adds genuinely new behavior: originals are read only inside the server process and never returned to the model, a notice is prepended to the response, size and file-type limits apply, and redaction is heuristic and may miss custom formats. These are exactly the traits annotations cannot express.

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?

Front-loads what the tool does and its safety guarantee before constraints and caveats. Every sentence carries distinct information (output shape, routing, limits, honesty about heuristic gaps); nothing is redundant padding.

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?

With no output schema, the description still describes the return value (redacted content plus findings summary and a leading notice), covers the input contract, failure modes (binary, oversized, non-regular files), and the security-relevant limitation of heuristic redaction. Nothing an agent needs to call it correctly is missing.

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% and the single path parameter is already documented with accepted path forms, so the baseline is 3. The description adds real value by clarifying that a path (not file contents) must be passed and that only regular files within 1 MiB are accepted, tightening how the parameter is supplied.

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 (reads a local text file and returns content with secrets replaced by [REDACTED]) plus the secondary output (findings summary with type, count, line numbers). It also implicitly separates itself from the sibling redact_text by specifying 'Pass a path, not file contents' and from Read/cat by naming them 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?

Explicitly says when to use it ('use this instead of Read or cat for .env files, config files, logs, key files') and enumerates when not to (directories, pipes, devices, binary files, files over 1 MiB). The 'pass a path, not file contents' clause routes the agent away from the text-based sibling.

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