redact_text

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

Without annotations, the description carries full burden. It discloses core behavior (remove and replace with black rectangle) and logging via reason, but does not address reversibility, permissions, or impact on tracked changes. Adequate but shallow.

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?

The description is concise: two introductory sentences followed by a clear argument list. No unnecessary words, though the args could be formatted as a table. Effectively front-loaded with purpose.

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?

Given the presence of an output schema, the description does not need to detail return values, but it could mention the mutation's effect on the document state. The description provides sufficient context for a redaction tool with 4 parameters.

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?

With 0% schema description coverage, the description adds meaning for all parameters: pattern (regex), para_ids (optional scope), exact_text (exact match), reason (audit log). This significantly aids parameter understanding beyond 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?

The description explicitly states 'True redaction: remove text and replace with black rectangle', using a specific verb-resource pair and distinguishing this tool from siblings like 'delete_text' or 'replace_text' by highlighting the unique outcome of a black rectangle.

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 description mentions 'Use exact_text or pattern', providing a hint for invocation but lacks explicit guidance on when to choose this tool over alternatives (e.g., delete_text, scrub_pii, replace_text). No when-not-to-use or exclusion cases are stated.

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