Skip to main content
Glama

Report advisory accessibility findings

audit

Reports advisory accessibility findings from a fresh current-screen capture—undersized touch targets, unnamed controls, and covered controls—without changing the device.

Instructions

Report advisory accessibility findings from one fresh capture of the current screen: touch targets below the platform recommendation, controls without an accessible name, and controls the snapshot already marks covered. Findings are review prompts, not failures, and the audit changes nothing on the device. Times out after 90s.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "audit"
  }
}

Input Schema

NameRequiredDescriptionDefault
udidNoApple device or simulator UDID.
deviceNoDevice name; ids go in udid or serial.
serialNoAndroid, HarmonyOS, or Vega VVD serial.
sessionNoSession name.
platformNoDevice platform.
deviceTargetNoDevice form factor.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.21.38

TDQS

A3.6/5.0
Behavior3/5

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

Adds real context beyond the annotations: findings are advisory, the audit 'changes nothing on the device', and the call times out after 90 seconds. The readOnlyHint=false flag is not contradicted, since a fresh capture still produces state, but the description does not explain why the call is not read-only or what the capture costs. The timeout is useful, but there is no disclosure of output shape or how many findings to expect.

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

Conciseness5/5

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

Two sentences, front-loaded with the core action and the enumerated finding types, then closing on the two constraints that affect decision-making (advisory status, no mutation, 90s timeout). No filler or restatement of the tool name.

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 read-ish diagnostic with six fully documented optional parameters and no output schema, the definition covers what it does, what it returns categorically, and its key limits (advisory, non-mutating, 90s). The remaining gap is the return format and how the agent should act on findings, which the description leaves to inference.

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

Parameters3/5

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

Schema coverage is 100%, so device selectors (udid, device, serial, session, platform, deviceTarget) are already documented in the schema. The description adds no semantics about which identifier to supply when several exist, nor about default behavior with zero required parameters. Baseline 3 applies when the schema carries the load.

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

Purpose4/5

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

States a specific verb and resource ('Report advisory accessibility findings') and enumerates the exact finding categories: undersized touch targets, unnamed controls, and controls the snapshot marks covered. It also pins the input to 'one fresh capture of the current screen', so the agent knows the audit is against live state rather than stored data. It stops short of naming the sibling (snapshot) that produces the same capture, so differentiation is implied rather than stated.

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

Usage Guidelines3/5

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

The description frames findings as 'review prompts, not failures', which tells the agent how to interpret output but not when to choose this tool over a plain snapshot. 'One fresh capture of the current screen' hints that the tool captures rather than reuses existing state, but there are no explicit when-to-use or when-not-to-use conditions and no named alternative.

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