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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint as true/false. The description adds valuable behavioral context: it discloses that errors never raise a protocol error but return an error object, and that every call is safe to retry after correction. This goes beyond the 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 compact, front-loading the key purpose ('Score and rank up to 20 headlines, best first. FREE.'), then providing a quick example, usage guidance, and error behavior. Every sentence serves a distinct purpose with 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?

Given the tool's low complexity (one parameter, simple input/output), the description fully covers purpose, usage guidelines, behavioral traits, error handling, and sample response. The output schema exists, so return values are already documented. The description is 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?

Schema coverage is 100%, providing a clear description of the 'headlines' parameter as an array of strings with a limit of 20. The description adds meaning by showing a typical input example and clarifying that only the first 20 are scored, which complements the schema. No additional parameter details are needed.

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 uses specific verbs ('score and rank') and resource ('headlines'), clearly stating it operates on up to 20 headlines and returns them best-first. It distinguishes itself from siblings by mentioning what it does not handle (email subject lines for subject_line_scorer, body prose for analyze_writing).

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 explicitly states when to use: 'when several title options need ranking.' It also clearly states when not to use: 'Not for email subject lines... or for body prose,' and names the alternative tools (subject_line_scorer, analyze_writing).

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