a11y-scorer

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states the audit purpose, but does not disclose what the tool returns (e.g., issue list, pass/fail result), whether any side effects occur, or if it requires authentication. 'Audit' implies read-only but is insufficient for an agent to anticipate the output.

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 a single, front-loaded sentence with no filler. Every word ('Audit', 'raw HTML', 'WCAG 2.1 AA issues') adds distinct value. It is appropriately concise.

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 only one parameter and no output schema, the description is minimally viable: it states the tool's core function and input. However, the absence of annotations and output details leaves gaps about expected results and edge cases, so it is not fully complete for an agent invoking the tool.

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 0%, so the description must compensate for the 'html' parameter. The description's 'raw HTML' directly explains the parameter's meaning, but it lacks extra context like expected format (full document vs. fragment) or encoding constraints. This is a basic but adequate semantic contribution.

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 the specific verb 'Audit' and the resource 'raw HTML' with the standard 'WCAG 2.1 AA issues', clearly distinguishing it from siblings like a11y_audit_url (which audits URLs) and a11y_contrast/a11y_headings (which focus on specific aspects). The purpose is unambiguous.

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 phrase 'raw HTML' indicates the tool is for direct HTML input, implying it should be used when you have HTML code rather than a URL. While it doesn't explicitly name alternatives or exclusions, the context is clear enough for an agent to infer appropriate usage compared to sibling tools.

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?

With no annotations, the description carries the full burden of disclosing behavior. It mentions that the tool fetches a URL (a network operation) and returns a heuristic audit, which gives some transparency. However, it does not outline potential failure modes, authentication needs, or the nature of 'heuristic' (e.g., not a full conformance test), so some behavioral aspects remain unclear.

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 a single sentence, directly states the action and outcome, and contains no filler or redundant information. Every word contributes value, making it highly concise and well-structured.

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 tool with one parameter and no output schema, the description covers the core purpose adequately: it fetches a URL and returns a WCAG 2.1 AA audit. It does not detail the audit's return format, but given the absence of an output schema and the tool's simplicity, this is a minor gap. Overall, the description is sufficiently complete for an agent to understand the tool's function.

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 schema has one parameter 'url' with no description (0% schema coverage). The description's mention of 'Fetch a URL' directly clarifies that the url parameter is the URL to fetch and audit, effectively compensating for the lack of schema documentation. This adds meaning beyond the bare schema definition.

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 clearly states the tool's function: 'Fetch a URL and return a WCAG 2.1 AA heuristic audit.' It uses a specific verb ('fetch') and identifies the resource (URL) and the output (WCAG 2.1 AA audit), distinguishing it from the sibling a11y_audit_html which likely operates on HTML content.

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 implies the tool should be used when a URL is available to audit, but it does not explicitly state when to use it versus alternatives like a11y_audit_html or a11y_contrast. There is no mention of exclusions or preconditions, leaving usage context implied rather than explicit.

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?

With no annotations, the description bears full responsibility for behavioral disclosure. It only states the purpose, not what the tool returns (ratio vs. pass/fail), how bold/fontSize affect thresholds, or accepted color formats.

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 a single sentence with no filler, front-loaded with the verb and resource. Every word serves a purpose, making it appropriately concise.

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 has 4 parameters, no annotations, and no output schema, the one-sentence description is insufficient. An agent would lack critical details about output format, parameter semantics, and edge cases.

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 0%, and the description only maps 'foreground/background pair' to fg/bg. It does not explain the optional bold/fontSize parameters or expected input formats, leaving significant ambiguity.

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 a specific verb ('Evaluate') with a clear resource ('WCAG color contrast') and scope ('foreground/background pair'). This distinguishes it from sibling audit tools, making the purpose immediately clear.

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 implies when to use the tool (when you have a foreground/background pair to check), providing clear context. However, it does not explicitly state exclusions or alternatives relative to sibling tools.

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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states the core action but does not explain the output format, how invalid HTML is handled, or whether the outline is nested or flattened. This is a minimal 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?

The description is a single sentence, front-loaded with the action and resource, and contains no filler. Every word contributes to the meaning.

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 tool is simple (one param) but without an output schema, the description leaves the term 'heading outline' undefined. An agent may not know if the output is a list, a nested tree, or what heading levels are included. It is minimally adequate but not fully 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 description coverage is 0% and the description never mentions the 'html' parameter. The tool name and description imply that the parameter is the HTML input, but the description adds no concrete semantics about the parameter's format, requirements, or role beyond what the schema already states (name/type).

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 a specific verb 'Extract' with a clear resource 'heading outline from HTML', which precisely states what the tool does. It distinguishes itself from sibling tools like a11y_audit_url and a11y_contrast by focusing on heading extraction.

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 implies usage—use this to extract heading outlines—but provides no explicit when-to-use guidance or exclusions. It does not name any alternative tools or mention when one might choose a different a11y tool.

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