RatedWithAI accessibility checker

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

The annotations already establish that this is a read-only, idempotent, non-destructive, closed-world operation. The description adds useful behavioral context by saying it returns plain-English steps and a code example, and by clarifying that it does not perform scans. It does not cover auth or rate limits, but those are not central for this explanatory read operation.

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 and front-loaded: it first defines the use case, then gives examples, then states what it returns, then names the alternative for scanning. Every sentence carries useful selection or invocation information.

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 a single fully documented parameter, an output schema, and rich annotations, the description provides everything needed for correct selection and invocation. It covers purpose, usage boundaries, output nature, and sibling routing without redundancy.

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%, so the rule_id parameter is already documented. The description adds value by giving multiple concrete axe-core rule ID examples (color-contrast, image-alt, label, link-name) beyond the single schema example, helping the agent recognize valid inputs.

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 states a specific verb and resource: explaining an axe-core accessibility rule and how to fix it. It names the sibling tool scan_accessibility and explicitly distinguishes the two, so an agent can tell what this tool does without opening the 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 explicit when-to-use guidance, including the typical source of the rule ID from scan_accessibility, and explicit when-not-to-use guidance by directing site scanning to scan_accessibility. This is exactly the routing information an agent needs.

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?

Beyond the annotations (readOnly/openWorld/idempotent/non-destructive), it discloses mechanics and cost the agent cannot infer: it loads the live page in a real browser, runs axe-core, crawls up to two additional same-site pages, and takes 15-40 seconds. The extra-page crawl and the runtime are exactly the behavioral facts an agent needs for planning.

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 the usage condition, followed by behavior, runtime, and exclusions in a single tight paragraph. Every sentence carries distinct information; no filler or repetition of the title.

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?

Even though an output schema exists, the description still summarizes the return shape (0-100 score, letter grade, failing rules with example elements) and states runtime and crawl limits. For a one-parameter, open-world scanning tool, an agent has everything needed to select and call 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 coverage is 100% for the single url parameter, so the schema already documents format and examples. The description adds the meaningful constraint that the URL must be public (no login, no localhost/private network), but otherwise restates rather than extends the schema, which is the baseline-3 case.

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 names a specific verb and resource (scan a public website/web page for accessibility) and pins the scope to concrete standards (WCAG 2.1/2.2 AA, ADA, EAA, Section 508). It is functionally unmistakable next to the only sibling, explain_accessibility_issue, since one performs a scan and the other explains a finding.

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 trigger (user wants a public site checked for accessibility) and explicit exclusions: login-gated pages, localhost/private-network addresses, and pasted HTML. The when-not conditions are the ones an agent would otherwise get wrong, so 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.