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

Annotations already provide readOnlyHint=true and idempotentHint=true, so the description adds meaningful context beyond them. The local-only, no-upload behavior is explicitly disclosed, which is not implied by the annotations and addresses a real concern with review tools.

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 three sentences, front-loaded with the core purpose, then the return value, then the critical privacy note. Every sentence contributes meaningful information and there is no redundancy or filler.

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 description fully covers what the tool does, what it returns, its key constraint (no report upload), and its reference items (rating sheets). For a read-only tool with complete schema annotations and no output schema, it is contextually complete.

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?

The input schema has 100% parameter description coverage, so the description doesn't need to re-explain the parameters. It does link the 'sections' parameter to 'what to check in each section' and the 'focus' parameter to 'writing quality issues', but this adds minimal value 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 the action ('Get Lenny Zeltser's expert criteria'), the resource ('reviewing an existing IR report'), and the deliverable ('focused guidance for constructive critique'). It distinguishes itself from sibling domain-review tools by mentioning the IR-specific rating-sheet items (lens taxonomy, Information sheet).

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 clearly implies when to use it: when the user wants expert IR review criteria without sharing the report itself. The statement 'This server never requests your report and instructs your AI to keep it local' clarifies a key usage constraint. It doesn't explicitly name alternatives or exclusions, but the context is strong.

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