Score UI drift

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

Annotations already declare readOnly/idempotent/non-destructive/openWorld, and the description adds substantial behavior beyond them: server-side fetch, extraction of inline + linked CSS, custom-property parsing across stylesheets/style blocks/style attributes, no browser required, and ~24h per-URL caching. The caching and no-browser execution model are exactly the operational facts an agent can't get from the schema.

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?

Front-loaded with purpose, then failure modes, usage, exclusions, execution model, and return shape in a logical order. The long parenthetical definitions of each drift failure mode are dense but each earns its place by telling the agent what the score means; slightly longer than strictly necessary.

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?

With no output schema, the description fully specifies the return JSON shape ({ ok, url, scope, score, grade, pass, warn, fail, skip, total, tokensExtracted, checks[] }) and the execution model, leaving no gap an agent needs before calling or interpreting results.

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% for the single url parameter, including its default, so the schema already carries the semantics. The description only restates that the URL is a live page to scan, adding no format, validation, or edge-case detail beyond the schema. Baseline 3 applies when the schema does the heavy lifting.

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?

Specific verb ("Score") plus resource ("live URL for AI-generated UI drift") with the exact checks enumerated (12 checks across four named drift failure modes). It explicitly distinguishes itself from siblings by naming designesy_score and designesy_tokens_score, so an agent can route without opening any schema.

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 gives an explicit positive trigger ("Use this when you need to verify whether a site is drifting off its own declared token system"), names "When NOT to use", and routes to two concrete alternatives with the conditions that select them. Nothing is left to inference.

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