redaction

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

Annotations already declare readOnlyHint, destructiveHint=false, and idempotentHint. The description adds valuable context beyond annotations: the returned map is not stored anywhere and is the sole means to reverse redaction. This informs the agent about a critical non-obvious behavior. No contradictions found.

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 only two sentences, but both are packed with essential information: the purpose and the map's non-persistence. It is front-loaded with the action and resource, then delivers the critical behavioral warning. No wasted words.

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?

The tool is simple (3 params, 1 required, no nested objects) and has an output schema, so the description need not explain return values in detail. It already states it returns redacted text and a map, gives the use case, and warns about map storage. For an agent to call it correctly, nothing essential 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 description coverage is 100%, meaning all parameters are already well-documented in the schema. The description does not add any additional parameter-level meaning beyond what the schema provides. According to the rubric, with high coverage, a baseline of 3 is appropriate, and no extra value is contributed here.

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 clearly states the verb 'Replace', the resource 'people in a piece of text', and enumerates specific types (names, emails, phone numbers, etc.). It also provides the context of use ('before the text is sent to a model or a third party') and distinguishes itself from the sibling 'restore' by implying the inverse operation. This is a precise, unambiguous purpose.

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 gives a clear when-to-use context (before sending text to a model or third party) and hints at the complementary sibling by stating 'Keep the map: it is the only way to put the real values back', which implies restore is for reversal. However, it does not explicitly name the alternative or state when not to use this tool, so it stops short of a perfect 5.

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

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

Annotations already cover safety (readOnlyHint=true, destructiveHint=false, idempotentHint=true). The description adds context about the map source and the transformation effect ('sees what they actually wrote'), which is useful beyond the annotations. There is no contradiction; 'reverse' implies a pure transformation consistent with readOnlyHint.

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?

Two sentences, front-loaded with the action and then the purpose. Zero wasted words. The description is optimally sized for the tool's simplicity.

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?

The tool is simple with only two parameters and has an output schema (not shown but present). The description covers purpose, usage, and the map source. It does not mention error cases (e.g., missing map keys) but these are not critical given the tool's scope and the annotations. It is sufficiently complete for an agent to invoke it 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 100%, so the schema already documents both parameters ('The map returned by redact' and 'Usually a model's reply, containing stand-ins'). The description adds minimal new meaning by linking the map to redact's output and the text to a model reply, but it does not go beyond the schema baseline. A 3 is appropriate.

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 clearly states the action: 'Reverse a redaction using the map it returned.' It names the specific resource (redaction) and the method (reverse), and the sibling tool 'redact' makes the inverse relationship obvious. This unambiguously distinguishes it from redact.

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?

It provides explicit usage context: 'Use this on a model's reply so the reader sees what they actually wrote rather than the stand-ins.' This tells the agent when to apply it, and it implicitly contrasts with redact by describing the opposite operation. It lacks an explicit 'when not to use' but the context is sufficient.

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