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

There are no annotations, so the description must carry the behavioral burden. It usefully discloses static heuristic checks, no live URL/browser requirement, and optional RAG-powered fixes, but it does not clarify whether RAG enrichment triggers external calls, how 'optional' is controlled, or what the output shape is. That leaves a noticeable gap.

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?

Three sentences, each with a distinct job: definition, method, and usage. It is front-loaded with the core purpose and contains no filler.

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 2-parameter read-only check with a fully documented schema, the description covers what the tool does, how (static heuristics, optional RAG), and when to use it. It slightly falters by not describing the return shape or the precise trigger for RAG enrichment, but nothing needed to invoke it successfully is missing.

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 both html and context. The free-text description does not add detail about parameter format or edge cases, giving the baseline score of 3.

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 opening sentence names a specific verb ('Analyze'), a concrete resource ('an HTML snippet'), and an explicit goal ('WCAG accessibility issues'). It also distinguishes itself from live-scanning siblings by stating it works without a live URL or browser.

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 last sentence gives direct usage guidance: use it when a developer pastes HTML or asks about a component's accessibility. It does not explicitly name sibling tools or say when not to use them, so it misses the top tier.

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 burden of behavioral disclosure. It reveals RAG dependence, API key requirements, template fallback, and the verify-only-in-fix-mode behavior. This is substantial, though it does not disclose response shape details or potential error/rate-limit behavior.

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?

Three tightly written sentences front-load the purpose, then explain the mode switch, then disclose the credential dependency. There is no filler, and each sentence earns its place.

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 eight-parameter schema, high schema coverage, and absence of an output schema, the description covers the key behavioral branches and dependencies. It could be slightly more specific about the exact response shape, but it explains both modes and the key constraint, making it sufficient for an agent to select and call the tool 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%, so the baseline is 3. The description adds meaningful parameter-interaction semantics: html omission switches modes institution, and verify is 'Ignored in explanation mode.' This goes beyond a simple restatement of schema fields.

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 opens with a specific verb and resource: 'Get a RAG-powered fix OR explanation for a WCAG violation.' It clearly distinguishes the two operating modes (fix with html, explanation without) and is semantically distinct from siblings like aether_check_html and aether_verify_fix.

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 gives explicit conditional guidance: 'Pass html ... to get a concrete fixHtml' versus 'Omit html to get a rule-level explanation.' It also notes the ALLCHEMY_API_KEY requirement and fallback behavior. No explicit comparison with sibling tools is provided, but the mode-based guidance is clear enough for correct invocation.

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. It discloses the main behavior: scanning, RAG-powered fix generation, return data (violations paired with fixHtml, explanations, WCAG references), and the effect of maxFixes:0 and verifyFixes. It does not confirm whether the operation is read-only or requires special permissions, but for a scanner this is a strong 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?

Four sentences, each with a purpose: the first states the core action, the second names the return artifacts, the third gives a fast-path tip, and the fourth provides routing guidance. The most important information is front-loaded, and there is no filler.

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 moderate complexity of 6 params and a nested spa object, the description covers the essential decision points: what it does, what it returns, the scan-only option, and when to choose it. No output schema exists, but the description lists the key fields returned, making it complete enough for an agent to call it correctly. It could mention that url and spa are mutually exclusive, but the schema already does.

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 baseline is 3. The description adds context about the 'one-call' combined mode and mentions maxFixes:0 for scan-only, but the schema already documents that. It doesn't materially expand on the url/spa interaction beyond what the schema descriptions state.

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-resource pair: scan a URL or SPA for WCAG 2.1 AA violations and generate RAG-powered fixes in one call. It also includes the output shape (violations with fixHtml, explanations, technique references), which clearly distinguishes it from siblings like aether_check_html or aether_get_fix.

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 explicitly recommends this tool for accessibility auditing and tells the agent to use it when a developer asks to check or fix accessibility. It also provides a concrete alternative within the same tool (maxFixes:0 for scan-only). It doesn't explicitly name sibling tools or describe when NOT to use it, but the primary recommendation is clear.

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 behavioral disclosure burden. It usefully reveals the write-like side effect (records rating, reason_code, shipped code, feeds learning pipeline) and mentions the required API key. It does not disclose whether feedback can overwrite prior feedback, idempotency behavior, or error/return behavior, so it is adequate but not rich.

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?

Two sentences with no filler. The core action and key are front-loaded in the first sentence, the briefly important learning context and API key requirement follow in the second. Every sentence earns its place.

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 an 8-parameter mutation-like tool with no output schema and no annotations, the description covers the essential operational context: what it does, what records, the required key, and the intent behind submission. It could additionally explain where finding_id comes from or how failures surface, but the schema already handles the parameter details and the core call scenario is clear.

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 fully documents all eight parameters. The description adds a small amount of connective context by calling out rating, reason_code, and developerCorrection as the key recorded fields, but it does not meaningfully supplement the existing per-parameter descriptions.

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 ('Submit') and resource ('developer feedback on a previously returned WCAG fix/artifact') and anchors it to a concrete key ('finding_id'). It clearly differentiates this from the sibling scan/fix/verify tools by focusing on post-fix feedback rather than performing scans or fixes.

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 is used after a fix/artifact has been returned, and notes it is meant to help the pipeline learn from misses. However, it does not explicitly state when not to use it or name sibling alternatives as fallbacks, leaving the timing context inferable 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 provided, the description carries full burden. It discloses determinism, the engine used, and the specific returned metrics. It does not mention side effects (e.g., network requests, runtime, rate limits) or explicitly state it is read-only, which would be expected for a verification tool. The description is adequate but not comprehensive.

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 three sentences with zero fluff. It front-loads the purpose, then modes, then outputs. Every sentence contributes meaning, making it highly efficient.

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 complexity of 5 parameters and two modes, the description covers modes, required parameter relationships, and return fields. It leaves ambiguity about what happens if both url and fixedHtml are provided simultaneously, and whether baseline is mandatory for a delta in URL mode (schema marks it optional). These minor gaps prevent a perfect score.

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 baseline is 3. The description adds value by explaining the mode-dependent roles of parameters: url for URL mode, fixedHtml/originalHtml for snippet mode, and baseline for delta calculation. This clarifies relationships beyond the schema's individual descriptions.

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 ('verify'), resource ('WCAG fix'), and engine ('Playwright + axe-core'). It clearly distinguishes itself from siblings by claiming to be the authoritative 'did the fix work?' signal, and outlines two distinct modes (URL and snippet) with measurable outputs.

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 provides clear guidance on when to use each mode (URL preferred when a URL exists; snippet for pre-deploy diffing) and explains the purpose of the tool as post-fix verification. However, it does not explicitly compare with sibling tools like aether_check_html or aether_scan_and_fix, leaving the selection among them to inference.

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