WIA A11y Checker

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

Annotations cover safety (destructiveHint=false, idempotentHint=true, openWorldHint=true), and the description adds genuine context beyond them: expected latency (~1-2 minutes), input rejection rules for private/localhost addresses, and the epistemic limitation of automated checks. It does not explain why readOnlyHint=false (quota consumption / server-side caching noted only in the schema) or describe rate limits, so it stops short of full disclosure.

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 action and return shape, followed by the timing and caveat; every English sentence earns its place. The trailing Korean parenthetical largely restates the preceding English as a translation summary rather than adding new information, which is a minor redundancy.

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 carries the burden of explaining returns and does so (score, badge tier, top violations with CSS selectors), plus timing and input constraints. The one unresolved gap is the relationship to the a11y_get_result sibling — whether the check is synchronous or job-based — which an agent would need to call this correctly in a multi-step flow.

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%, so the schema already documents url, refresh (10-minute cache), and max_violations. The description reinforces the single-page and public-only constraint on url and ties outputs to 'the most important violations,' but adds no syntax or format detail beyond the schema. 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?

States a specific verb and resource ('Run an automated accessibility check (axe-core + Lighthouse) on ONE public http(s) web page') plus the outputs, so the agent knows exactly what the tool does. It never mentions or distinguishes itself from the sibling a11y_get_result, leaving some ambiguity about whether results are returned inline or must be fetched separately, which keeps it below 5.

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?

Gives clear operating context: one page at a time, public pages only, ~1-2 minutes runtime, and an explicit note that automated results cannot prove WCAG conformance and still need manual review. However, it never names a11y_get_result or states when to prefer an alternative, so no explicit when-not guidance exists.

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?

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world behavior, so the safety profile is covered. The description usefully adds the web-page-only scope constraint and the returned content ('summary... including top violations'), but says nothing about invalid or unknown IDs, error behavior, or truncation limits.

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?

A single, front-loaded sentence that leads with the action and resource, with no filler. The trailing Korean parenthetical duplicates the English sentence and adds no information for an English-speaking agent, a minor waste.

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?

For a read-only lookup with no output schema, the description covers the identifier format, the returned content, and a scope restriction, and annotations carry the safety profile. It is nearly complete, missing only guidance on failure modes and what max_violations controls.

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 50%: 'id' is well documented in the schema with pattern and example, but 'max_violations' has no description in either place. The description's phrase 'including top violations' faintly implies a bounded violation list but does not explain the parameter, its default of 10, or its 1-25 range.

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 ('Fetch the summary of a previously saved web accessibility check by its result ID'), specifies the ID format, and states what is returned ('including top violations'). It also scopes the tool with 'Only results of web page checks are returned,' which implicitly separates it from the a11y_check_url sibling, though it never names that alternative explicitly.

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?

Usage is only implied: 'previously saved' and 'result ID' suggest this retrieves an existing result rather than running a new check, but there is no explicit when-to-use or when-not-to-use guidance and the a11y_check_url sibling is never referenced. An agent must infer that it should run a check first to obtain an ID.

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