Skip to main content
Glama
kinti

a11y-toolkit

by kinti
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

a11y-toolkit: Evidence pack (countersignature-ready)

a11y_evidence
Read-onlyIdempotent

Build a WCAG A/AA evidence pack from audit reports: full 55-criterion matrix, human review effort estimates, SHA-256 hashes, and a signature block for vendor-neutral countersigning.

Instructions

Builds the COUNTERSIGNATURE-READY evidence pack: the machine→human handoff object for WCAG conformance work. Takes one or more audit reports (any mode — static, rendered, reflow, keyboard, scroll) and returns: the full 55-criterion A/AA matrix (automated-fail / automated-review / not-flagged — NOT pass / not-run / manual-only), each row priced with its human-effort class (MIN 1-3 / MED 5-10 / MAX 15-30 min of human review remaining) and total remaining minutes (the quote input for a review marketplace), every artifact SHA-256-hashed with timestamps, an empty signature block (name, credential, date) whose statement must reference the pack's own sha256, and the tamper-evidence rule stated. Vendor-neutral: any qualified human can countersign it. Evidence, never conformance. — The tier-3 handoff object; feed it every audit report you have.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
informesYesaudit report objects (any mode)
snapshotNoa11y_snapshot output (optional)
evaluadorNo{"nombre":…, "credencial":…, "fecha_revision":…} to prefill the signature block
verificadosNoCriterion codes an agent/human verified against this sample (manual checklist protocol) — they become agent-verified in the matrix; automated-fail stays fail

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv4.0.0
    • addedInput schema / properties / verificados
      Added value: +{
+  "description": "Criterion codes an agent/human verified against this sample (manual checklist protocol) — they become agent-verified in the matrix; automated-fail stays fail",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}
  2. Addedv3.12.0

TDQS

A4.5/5.0
Behavior5/5

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

Beyond annotations (read-only, idempotent), the description discloses rich output behavior: the exact matrix statuses, human-effort pricing, hashing with timestamps, empty signature block, and tamper-evidence rule. It also clarifies vendor neutrality. This consistently aligns with annotations, adding significant detail about what the tool returns.

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 lengthy but front-loaded with a clear purpose and organized as a colon-delimited list of outputs. Every sentence adds detail about the tool's behavior or scope. Slightly dense with parentheticals but not verbose or tautological.

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

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no output schema and four parameters, the description covers the primary return payload and how inputs like informes and verificados influence it. Optional snapshot and evaluador are only described in the schema, but the description names the signature block they would affect. Complete enough for a competent agent to invoke it correctly.

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

Parameters4/5

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 extra meaning by specifying that inputs are audit reports in any mode, that verified criteria become agent-verified in the matrix, and that the output includes a priced review quote. This connects parameters to output behavior beyond the schema's basic field descriptions.

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?

Clearly states the tool's function with 'Builds the COUNTERSIGNATURE-READY evidence pack' and enumerates the exact output components. Differentiates it from sibling audit/snapshot tools by positioning it as the tier-3 handoff object that consumes audit reports. The 'Evidence, never conformance' note further disambiguates its role.

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

Usage Guidelines4/5

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

The description says 'feed it every audit report you have,' giving concrete when-to-use guidance, and specifies that it accepts reports from any audit mode. It does not explicitly name sibling tools to use instead, but the tier-3 positioning implies it is the aggregation step after audits. Lacks explicit when-not-to-use clauses, but the context is sufficient for an agent.

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

Deploy Server

Other Tools