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

Beyond the annotations (readOnlyHint, idempotentHint, destructiveHint), the description adds critical behavioral details: error handling ('never raises a protocol error — it returns an error object with fix instructions') and idempotency guarantee ('after correcting the input it is always safe to retry'). No contradictions with annotations.

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 efficiently structured: purpose first, then examples, usage guidelines, error behavior, and idempotency note. Every sentence adds value. Minor extraneous text ('FREE') but overall excellent conciseness.

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?

Covers almost all aspects: what smells are detected, input/output format, error handling, usage context, and intentional limitations (signal vs. proof). The presence of an output schema further reduces the burden on the description. Very comprehensive.

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% with a clear parameter description. The description adds only a typical input example, which is helpful but does not significantly extend the schema's meaning. Baseline 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 begins with a specific verb and resource: 'Flag the tells of unreviewed AI-generated code in a source file.' It clearly identifies the tool's unique role among siblings (vs. review_diff) by focusing on full source files and AI smeels.

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 states when to use ('on a full source file suspected of unreviewed machine authorship'), when not to use ('Not on a diff'), and names the alternative tool ('review_diff'). It also clarifies the result is a 'signal to check, not proof of authorship,' setting proper expectations.

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