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

No annotations are provided, so the description carries the full disclosure burden. It discloses the runtime behavior of the generated code in useful detail: it logs every dynamic-region announcement with time, politeness, role and text, and renders a visible on-screen panel — exactly what an agent needs to predict the result. It does not restate safety/profile, but returning a code string is inherently side-effect-free.

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 with the artifact and its behavior, using a parenthetical for the deployment modes. No filler, though the em-dash clause packs several details densely.

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 must convey what the tool yields, and it does by enumerating the logged fields and the visible panel. For a one-optional-param code generator this is essentially complete, with only the exact return shape left implicit.

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% and the single optional lang param is fully documented in the schema ('monitor panel language (es default)'), so baseline 3 applies. The description adds no meaning beyond the schema about the parameter.

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 (Returns) and resource (injectable JavaScript for an aria-live announcement monitor), and clarifies the artifact type an agent will receive. This is clearly distinguishable from every sibling (audits, contrast, diff, keyboard), which instead measure or mutate a page.

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 parenthetical '(bookmarklet or page.evaluate)' implies the two deployment contexts, giving implied usage guidance. However, there is no explicit when-to-use/when-not-to-use statement or named alternative, so the agent must infer the scenario.

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 and does so well: it discloses the Playwright/Chromium runtime dependency with the exact install command, describes what each check measures (alpha compositing, 24×24 targets), and states that findings include remediation. It stops short of describing failure modes, rate limits, or output shape.

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 dense paragraph that front-loads the primary purpose before the parenthetical criterion list and ends with the prerequisite. The criterion parentheticals are information-rich, though slightly heavy; every clause 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 a 3-param tool with no output schema and no annotations, the description covers purpose, scope, checks, remediation output, and runtime prerequisites well. The gap is parameter-level semantics, which is the one area left thin.

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 33% – url and lang have no descriptions, and only timeout is documented in the schema. The description adds nothing about the parameters (no URL format, no explanation of the lang enum's effect on locale-specific checks), so it fails to compensate for the coverage gap.

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?

Names a specific verb+resource ('deep RENDERED WCAG audit via local Playwright/Chromium') and enumerates the exact checks performed with WCAG criterion numbers. It also implicitly distinguishes itself from a11y_audit_url by describing 'rendered versions of the static checks'.

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 'Deep RENDERED' framing and the 'rendered versions of the static checks' phrase imply this is the heavier Playwright-based counterpart to the static a11y_audit_url, but no explicit when-to-use or when-not-to-use guidance is given. An agent must infer the routing from the adjective 'deep'.

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 and does well: it discloses the coverage limitation (~1/3 of WCAG), that it is automation-only, that each finding includes remediation, and that output is a weighted 0-100 score. It omits fetch-failure/network error behavior and single-page vs crawl semantics for 'pages'.

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 purpose and the closing routing sentence are front-loaded and well-placed, but the middle is a long wall of signal names and SC numbers that is heavier than an agent strictly needs to select the tool. It is dense rather than wasteful, so still serviceable.

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 complex tool with no annotations and no output schema, the description covers scope, scoring model, remediation inclusion, and interpretation limits. Return-value structure is not detailed, but the key decision-relevant context is present.

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 the url/html relationship ('or an HTML string') but does not expand on crawl aggregation, timeout, or the lang default beyond what the schema already states.

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 ('Express WCAG 2.2 audit of a URL or an HTML string') and enumerates the exact signal set with WCAG SC references. An agent can distinguish it from siblings like a11y_audit_dom or a11y_diff_urls 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?

Explicitly frames the tool as a 'filter, not verdict' and routes the agent to a11y_criterion to interpret a criterion, plus notes html overrides url. It stops short of contrasting with the closest sibling (a11y_audit_dom), so the when-to-use guidance is clear but not exhaustive.

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?

No annotations exist, so the description carries the full burden, and it does well: deterministic behavior, a closed fix list, explicit non-goals, and the return shape (fixed_html + aplicados + no_aplicados). It omits idempotency/auth details, but for a pure HTML-string transform those are minor.

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-loads the core purpose, but the single dense paragraph contains marketing noise ('the honest anti-overlay') and mixed Spanish identifiers that reduce scannability. Trimmed, it would be sharper.

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?

There is no output schema, so the description compensates by naming the return keys and the no_aplicados reason/remediation behavior. Combined with the 100%-covered input schema, an agent has what it needs to invoke and interpret 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 100%, so baseline is 3. The description restates the schema conditions ('fill missing html lang and empty title when provided'), adding only marginal meaning beyond the schema's own conditional wording.

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+resource ('deterministic safe auto-fixes applied to HTML') and enumerates the closed list of fixes, which clearly differentiates it from the surrounding a11y audit/suggestion siblings. An agent can tell this is a fixer, not an auditor, 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?

Explicitly gives the when-not boundary: 'Everything requiring judgment (alt text, contrast, accessible names) is NOT touched' and routes those cases to no_aplicados with remediation. It does not name a specific sibling alternative, but the exclusions are clear enough to select correctly.

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 and does well: it discloses the output format (accessible SVG), contents, color-coding behavior, and a deliberate semantic constraint ('does NOT say conformant', automated screening ≈ 1/3 of WCAG). It doesn't state permissions or side-effect behavior, but for a read-only badge generator this is solid 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?

Two sentences, front-loaded with the core action and payload, and the remaining sentence adds a distinct behavioral caveat. Stylistic touches ('HONEST', the honest seal) cost a little density but don't obscure 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?

With no output schema, the description correctly describes the return value (SVG contents) and the scope caveat, which is what an agent needs to route and use it. The unmentioned 'lang' parameter and lack of precise formatting details keep it short of 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 coverage is 67%, and the description echoes some meaning ('color-coded by score', 'date ... scope') that overlaps the schema's own field descriptions. The 'lang' enum parameter is untouched in the description, and no extra format guidance (e.g. how scope is derived) is added, so it sits at the 3 baseline.

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 ('Returns an ... accessibility badge as accessible SVG') plus the payload it carries (score, date, scope), so the agent knows exactly what it produces. It never names a sibling, so a 5 for explicit sibling differentiation isn't earned.

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 an intended context ('Embed it in audited sites or statements') and implies an audit must precede it, which is useful. It offers no explicit when-not condition or comparison against alternatives like a11y_generate_declaration.

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?

No annotations exist, so the description carries the full burden, and it does disclose the computation method (pixel-level sampling of real background) plus the return semantics (worst/median/p95 ratio, % area passing AA, 3x3 hostile-zone detection). It omits auth requirements, failure modes, and error behavior, keeping it short of a 5.

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-loads the core purpose ('TEXT OVER IMAGE contrast') and packs detail densely with no filler sentences. The telegraphic arrow style and untranslated jargon ('zona_peor') slightly reduce immediate legibility.

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 annotations, no output schema, and 4 of 5 parameters undocumented at 0% coverage, the definition is materially incomplete for a tool whose inputs are non-obvious. It describes outputs well but leaves an agent unable to confidently supply sample, lang, or text_color format.

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% across 5 parameters, so the description must compensate, but it only documents region as 'x,y,w,h' and implies it is recommended. path, text_color, sample, and the lang enum (es/en) are left entirely unexplained in both schema and description.

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+resource (contrast measurement for text over images via pixel-level sampling) and explicitly carves out what it is not: 'What pair-only checkers cannot do,' directly contrasting with the sibling a11y_contrast_pair. An agent can distinguish this from the pair checker without opening either 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?

The phrase 'What pair-only checkers cannot do' implies the tool is for real-background image cases rather than flat color pairs, and 'region=... recommended' hints at expected usage. However, it never states explicitly when to prefer this over a11y_contrast_pair or a11y_audit_url, leaving selection to inference.

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 and discloses useful behavior: accepted color syntaxes, alpha compositing over background, and a fallback suggestion when AA fails. It does not detail the exact return structure, but covers the key behavioral traits for a computation tool.

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-loaded with the core purpose and then criteria, followed by input handling and fallback behavior. No filler or repetition.

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 simple computation tool with no annotations and no output schema, the description covers purpose, input formats, alpha compositing, and failure behavior. It could specify the exact return shape (e.g., ratio value plus pass/fail per criterion) but is largely sufficient.

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 only 33% (only lang has a description), so the description must compensate. It specifies the accepted color formats for fg and bg and explains alpha handling, adding meaning beyond what the schema provides.

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 operation: 'Exact WCAG contrast ratio for a color pair' with per-criterion WCAG verdicts. It clearly distinguishes itself from sibling a11y_contrast_image by operating on two colors rather than an image.

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 for evaluating a specific color pair, but gives no explicit guidance on when to choose this over siblings like a11y_suggest_color or a11y_audit_url. The failure suggestion is a feature, not a usage directive.

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?

No annotations are supplied, so the description carries the burden, and it does well: it discloses the return shape (requirement, typical failures, verification, tool-to-criterion mapping) and the bilingual es/en behavior. It does not state that it is read-only or offline/lookup-based, but nothing about it is misleading.

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, front-loaded with what it does and ending with the when-to-use rule. The inline code examples are slightly redundant but cheap and genuinely reduce ambiguity about the input format.

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 and no annotations, the description must carry the return-value burden and it does, enumerating what the explanation contains. Minor gap: no hint about failure behavior for an invalid code or whether codes map to WCAG 2.1 vs 2.2.

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% (only 'code' documented). The description compensates by giving concrete code formats ('1.4.3', '2.5.8', '4.1.2') and the es/en language pair, effectively documenting the undocumented lang parameter's purpose.

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 ('Explains') and resource ('a WCAG 2.2 success criterion') with contents spelled out: requirements, typical failures, and verification mapping. This clearly separates it from the audit/contrast/autofix siblings, which measure or mutate rather than explain.

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 explicit trigger conditions: 'Use it whenever you need to explain WHY a finding matters or what the criterion actually says.' That is a clear usage context, though it does not name a specific sibling alternative to prefer for the lookup-adjacent case.

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?

No annotations exist, so the description carries the full burden. It usefully discloses the return convention ('ok=false means a regression to review') and the dual input mode, but says nothing about limits on snapshot size, whether inputs must be produced by a11y_snapshot, or any failure/side-effect 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?

Two dense sentences, zero filler, with the core purpose and the diff contents front-loaded ahead of the ok=false convention. Every clause carries 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?

With no output schema, the description does the right thing by explaining the ok=false return meaning. Combined with 100% schema coverage on both params, an agent can invoke it correctly; only the sibling-boundary (vs a11y_diff_urls) is left open.

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% and both parameter descriptions already state BEFORE/AFTER and 'inline JSON or path'. The description's input-mode sentence simply restates that, adding no new syntax or format detail, so the baseline 3 applies.

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?

Names a specific verb+resource ('Regression diff between two accessibility snapshots') and enumerates what the diff contains (added/removed/renamed interactives, focus-order changes), which is far more specific than the bare name. It does not, however, distinguish itself from the sibling a11y_diff_urls, which is the most likely confusion point.

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 parenthetical 'before/after a deploy' implies a regression-review use case, so usage is inferable. There is no explicit when-to-use-this-vs-a11y_diff_urls guidance and no stated prerequisite (e.g., that inputs must come from a11y_snapshot).

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 behavioral burden. It discloses the environment prerequisite (local Playwright), which is genuinely useful, but says nothing about network access, permissions, what gets compared, pagination/limits, or what a diff output looks like.

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 tight sentence that front-loads the operation and appends the prerequisite and an example. No filler or 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?

For a two-URL comparison tool with no annotations and no output schema, the description omits key operational details an agent needs: authentication requirements, expected return shape, and any rate or duration limits.

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 both required parameters (url_a, url_b) are bare strings. The description's example clarifies that the two URLs are meant to be compared but does not specify ordering, format, or whether they must be same-origin.

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 compound verb (snapshot and diff) on a specific resource (two URLs), with a concrete example (staging vs production). It is distinguishable from a11y_snapshot and a11y_diff, though naming it as a one-call convenience over those siblings would sharpen it further.

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 parenthetical example implies the intended use case of comparing two environments, but there is no explicit when-to-use guidance or routing to alternatives like a11y_snapshot plus a11y_diff. Usage is implied rather than stated.

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. It does disclose two useful behaviors: the output is itself accessible, and it writes to output_path when provided. It omits whether an existing file is overwritten, whether HTML is also returned when output_path is absent, and any permission/auth requirements.

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 dense sentences, front-loaded with the core action and framework mapping; no filler. Sentences are long and parenthetical-heavy, but every clause carries 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?

For a 13-parameter generation tool with no annotations and no output schema, the description is under-specified: the meaning of the required estado enum and most optional content fields is nowhere available, so an agent cannot reliably fill the required inputs.

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 only 8% across 13 parameters, so the description must compensate and largely does not. It meaningfully explains marco's two values and lang's effect on wording plus output_path, but leaves the required parameters entidad, url and especially the estado enum (plena/parcial/no_conforme), metodo, feedback, reclamacion, dates and the two content fields entirely undefined.

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 artifact ('Generates an Accessibility Statement in HTML') plus the two regulatory regimes it can produce, which clearly separates it from the audit/contrast/diff siblings. It never names a sibling, but the generated-resource framing 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?

Gives real guidance on which framework/regime applies ('Spanish public sector' for rd1112 vs EAA/Ley 11/2023 for eaa), which is effectively usage guidance for the marco parameter. However it offers no condition for choosing this tool over alternatives or any prerequisite/ordering guidance (e.g. audit first to determine estado).

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 and does so: up to 60 real tab stops, cycle detection logic, the Escape-release decision rule, severity classification, and the environment prerequisite ('Requires local Playwright'). It also notes it returns the full tab stop list, covering return behavior in the absence of an output 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-loads the criterion and core mechanism, then layers the decision rule. Dense but each clause (Escape test, severity, Playwright requirement, return value) earns its place; slightly long with the mid-sentence em-dash asides.

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?

No output schema and no annotations, so the description must cover results and safety/context — it names the returned tab stop list and the local-Playwright requirement, which is substantial. The lang parameter's effect and the shape of severity output remain unstated, leaving a modest gap.

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 only 33%: url and lang have no schema descriptions, and the description never explains what lang (es/en) controls or what url should point to. It tangentially touches max_pasos via 'up to 60 real tab stops,' but that default is already documented in the schema, so it adds little and leaves two parameters unexplained.

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+resource: keyboard-trap detection for WCAG criterion 2.1.2 via real Tab walking in Chromium. The scope ('cycle detection... does ESCAPE release the cycle?') distinguishes it clearly from sibling tools like a11y_audit_url or a11y_audit_dom, which are broader audits.

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 strong context on when it fires and how results are judged: a modal that cycles and releases on Escape is correct and NOT reported, while an unescapable cycle is high severity. It implies the target scenario (modal/dialog keyboard behavior) but never explicitly names when to prefer siblings like a11y_audit_url over this narrow check.

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 and does well: it discloses the measurement procedure (load at 1280px, then 320px), what is returned (real horizontal scroll and the overflowing elements), and a hard prerequisite ('Requires local Playwright'). It omits auth/network/rate-limit traits and does not restate that the operation is non-mutating, but the operational profile is largely conveyed.

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 purpose and criterion before the method detail, and every sentence carries information (scope, output, prerequisite). The parenthetical method note about zoom re-layout is defensible justification but lengthens the definition more than strictly needed.

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?

No output schema or annotations exist, so the description is the only source of behavior — it covers procedure, output shape and environment requirement well. However, two of three parameters (lang, timeout) are left entirely unexplained, leaving the agent unable to populate them confidently.

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% across 3 parameters, so the description must compensate, and it does not: only 'url' is implicitly explained ('Loads the URL'). The 'lang' enum and 'timeout' parameters are completely undocumented in both schema and description.

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 check ('Reflow check at 320px') tied to a named WCAG criterion (1.4.10 AA), which cleanly separates it from the generic a11y_audit_url sibling. It also explicitly claims the niche of checks 'axe and Lighthouse do not automate', so an agent can place it 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?

Gives a clear context for use: this is the tool for 1.4.10 reflow verification that automated scanners miss. It does not name a sibling alternative or state when-not-to-use, so it stops short of full routing guidance.

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 full burden and does disclose real behavioral traits: it drives scrolling batches in Chromium, runs a live-region observer, checks focused-element survival across re-renders, and skips signals with a note when no standard items are found (login walls). It also discloses the environment requirement. It omits return format and any timing/rate caveats.

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 core scoping clause is front-loaded, but the body is padded with rhetorical framing ("the documented disaster nobody automates") and a stack of parenthetical checks. It is readable but under-tightened for the information delivered.

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 3-param tool with no annotations and no output schema, the description explains the checks performed but never describes what the caller receives back (findings, structure, scoring), which is a real gap when no output schema exists. The behavioral and guard coverage is good; the result contract 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 coverage is only 33%: only max_tandas has a schema description, while url and lang (an enum) are bare. The description implies batching semantics ('Real scrolling batches') but does not explain url, what lang changes, or how many batches are useful. It only partially compensates for the documentation gap.

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: an accessibility audit of infinite-scroll behavior, with named criteria (2.4.3, 4.1.3, 2.2.2). That scope is clearly distinct from siblings like a11y_keyboard or a11y_contrast_image, though it never names any sibling explicitly. The editorializing ("the documented disaster nobody automates") adds noise but does not obscure the purpose.

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 implied by the scope (audit a page that lazy-loads content on scroll), and a prerequisite is stated ("Requires local Playwright"). However, it never states when NOT to use it or which sibling (e.g. a11y_audit_url, a11y_keyboard) to prefer for related focus/announcement checks. No explicit routing guidance.

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 and does well: it discloses the runtime prerequisite ('Requires local Playwright') and a conditional capability ('when Playwright ≥1.49 is available the computed ACCESSIBILITY TREE'), so the agent knows output varies by environment. It omits return format/size and any auth or failure behavior, keeping it short of 5.

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 core purpose, then packs the output contents, version caveat, and workflow into two tight sentences. Dense but every clause carries information; minor cost is the parenthetical stacking.

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?

No output schema exists, so the description appropriately enumerates the return contents, and it covers the key prerequisite. For a single-required-param snapshot tool with no annotations, this is close to complete; only pagination/size limits and failure modes are unaddressed.

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 0% and the single 'url' parameter has no schema description, but the description supplies the meaning ('snapshot of a URL', i.e., the page to capture). That is sufficient for a one-parameter tool, though it adds no format constraints or protocol requirements.

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+resource ('Accessibility snapshot of a URL') followed by a precise inventory of what it captures: interactive elements with tag/role/name/href, real tab focus order, and the computed accessibility tree. It is clearly distinguishable from siblings like a11y_audit_url or a11y_keyboard 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?

Gives an explicit workflow ('Save it before a deploy and compare after with a11y_diff'), naming the alternative tool for comparison. It does not, however, say when to prefer this over a11y_audit_url or a11y_audit_dom, so the sibling routing is incomplete.

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?

No annotations, so the description carries the full burden. It discloses the algorithm (nearest opaque color using RGB distance) and that it returns the color, its ratio, and whether it lightens or darkens, which is helpful. However, it omits whether the suggested color is guaranteed to meet the target, how ties are handled, and any failure 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?

A single, information-dense sentence that front-loads the most important details (what it returns, the algorithm) with no wasted words.

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 3-parameter function with no output schema and no annotations, the description covers the return concept and default target but lacks details on the color input format, edge-case behavior, and guarantees (e.g., if target is unreachable). It is minimally sufficient but leaves gaps.

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?

With 0% schema description coverage and 3 parameters, the description only partially compensates: it states that fg and bg are colors and target is the ratio (default 4.5), but the parameter names (fg, bg, target) are still not explicitly linked, and the color format (e.g., hex, rgb) is not specified.

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 (suggest) and resource (color), describes the algorithm (nearest opaque color by RGB distance), the goal (reaching a target contrast ratio against bg), and the expected output. Clearly distinct from siblings like a11y_contrast_pair which checks contrast.

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?

Implied usage is clear from 'suggest' and the contrast target, but there are no explicit when-to-use/when-not statements or references to alternatives like a11y_autofix or a11y_contrast_pair.

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