Skip to main content
Glama

Check a fix before deploying it

validate_fix
Read-only

Before deploying ANY accessibility fix, validate it here first — every time, on every rule, not only when you are unsure. It is free, instant, loads no page, and it catches the fix that merely hides the problem from the next scanner. Send the markup you are about to deploy and get a verdict on whether it actually fixes the rule it targets. Four answers: "resolved", "not_resolved" (with what still fails), "masked", or "not_decidable_from_markup". Call it after editing and before deploying, on the rule id and htmlSnippet from list_violations — it reads markup only, so iterating costs nothing against the page allowance. Check the finding's "markupValidatable" first: every list_violations finding carries it, and false means this tool has no markup check for that rule and will refuse it, so the call is wasted. Easiest way to call it: pass "finding" — the findingId from a list_violations entry — and "rule", "before" and the measured colours are filled in from the stored finding for you; anything you pass explicitly wins over them, per field. "masked" is the answer worth having: deleting the element, adding aria-hidden, hiding it with display:none, dropping the visible text or turning a into a all make a scanner go quiet while leaving the barrier in place, so a later re-scan would wrongly agree with you. Never treat it as resolved. Pass "before" whenever you have it — deletion, lost text and downgraded controls are only detectable by comparison. For a contrast rule, pass "colors" — the foreground and background you intend to ship, plus fontSize and fontWeight for large text — and the ratio is computed against the WCAG threshold and answered outright, with the nearest passing foreground when it still fails. Colours declared inline on the markup are read automatically. Without a colour pair contrast stays undecidable, because a fragment has no computed colour. It cannot judge anything else that depends on rendering: focus indicators, forced-colors, reduced motion, tap-target size, reflow at zoom, keyboard traps and reading order all come back "not_decidable_from_markup", naming the tool that can answer them. It also refuses rules it has no check for rather than guessing, so a "resolved" means something. Each markup argument is capped at 100KB; going over is reported, not silently trimmed, and a truncated fix is never called resolved. Read-only — it does not touch the site, the scan history or the findings.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
ruleNoThe rule the fix targets — the "ruleId" from a list_violations finding, e.g. "image-alt", "button-name", "label", "aria-hidden-focus", "tabindex". Required unless you pass "finding", which carries it: the same markup passes one rule and fails another, so there is no useful answer without it.
afterYesThe markup you intend to deploy, with your change applied.
beforeNoThe original markup, normally the finding's htmlSnippet verbatim — or supplied by "finding". Optional but worth having: without it only absolute masking signals (aria-hidden, hidden, display:none) can be detected, and deletion, removed text and downgraded controls cannot.
colorsNoFor contrast rules only: the colour pair the fix proposes. With both colours the verdict is closed-form arithmetic rather than a refusal. Pass only the colour you are changing when you also pass "finding" — the rest comes from the measurement.
findingNoThe "findingId" of a list_violations entry, e.g. "clx9f2k4b0001". Pass it and the rule, the original markup and — on a contrast rule — the measured foreground, background, font size and weight are read from the stored finding, so nothing has to be transcribed. Only findings on this website resolve. Anything you also pass explicitly wins over the stored value, field by field.
websiteYesThe website domain as registered in Inclusify, e.g. "example.com".

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already say readOnlyHint=true and destructiveHint=false, and the description reinforces this with 'Read-only — it does not touch the site, the scan history or the findings.' It adds substantial behavior beyond annotations: no page load, 100KB cap, refusal rather than guessing, the meaning of 'masked', and the four possible verdicts. There is no contradiction with the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the primary use case and is densely informative, with almost every sentence earning its place. It is quite long and would benefit from bulleted or sectioned structure, but the complexity of the tool justifies most of the length and there is little true redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

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 must and does explain return values: the four verdicts, what 'masked' means, and that failures name the remaining issue. It also covers limitations, prerequisites, size caps, and the rule-parameter requirement, making it complete for an agent to select and invoke correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Even though schema coverage is 100%, the description adds critical cross-parameter semantics: 'finding' can carry rule/before/colors, explicitly passed values override stored ones, 'before' enables deletion/lost-text detection, and 'colors' enables WCAG contrast arithmetic. These nuances are absent from the schema and materially change how the tool is invoked.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly names the verb (validate), resource (an accessibility fix's markup), and intended moment (before deploying, after editing). It distinguishes this tool from the sibling list/set tools by focusing on verdicts like 'resolved', 'masked', and 'not_decidable_from_markup', so an agent can confidently pick it.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit when-to-use guidance ('every time, on every rule, not only when you are unsure') and when-not-to-use guidance: check 'markupValidatable' first, and rendering-dependent checks are refused. It also connects to list_violations findings and tells the agent how to invoke with a findingId, making the call path unambiguous.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.3/5.0
Disambiguation4/5

The descriptions do exceptional cross-referencing work, explicitly separating near-neighbor pairs (add_website vs add_domain, list_alt_findings vs check_page_alt_text, plan_options vs billing_link, widget_status vs widget_usage). A few clusters remain that an agent could confuse without reading carefully, notably site_overview vs compliance_status (both report statement existence and scan-record state) and crawl_summary vs list_monitored_pages vs site_overview (all touch coverage numbers). Overall, distinct purposes are clearly delineated despite the large surface.

Naming Consistency4/5

All names are lowercase snake_case with strong family patterns: list_* (5 tools), add_* (3), set_* (7), plus org_* and *_history pairs. The main inconsistency is the mix of verb-led names (list_violations, set_slack_channel, start_crawl) with noun-led read names (site_overview, compliance_status, widget_usage, next_steps), but the noun-led names follow a coherent 'what it returns' vocabulary (status, summary, history, overview, rollup). Minor deviations rather than chaos.

Tool Count3/5

36 tools is heavy and sits above the 25-tool threshold where agent navigation starts to degrade, but the server covers a genuinely broad domain: website lifecycle, monitoring, four finding types, four live-audit tools, seven config setters, org rollups, billing, and CI. Most tools earn their place and none are duplicates, but several could plausibly be merged (set_slack_channel/set_slack_events/set_monitoring_settings into one notifications tool; list_violations/list_alt_findings/list_content_findings with a filter). The count is on the edge of unwieldy for an agent's tool-selection step.

Completeness3/5

The read/audit/analysis side is rich and well-covered: findings, history, live checks, org rollups, coverage, and validation all have tools. However, the write side is one-directional: add_monitored_pages is explicitly add-only, and there is no remove_website, remove_domain, or remove_monitored_pages, so teardown and 'stop monitoring this page' requests hit dead ends that the descriptions acknowledge belong to the panel. Statement content writing and widget installation are also panel/browser-only by design, which is documented but still leaves those operations outside the agent's reach.