Skip to main content
Glama
Sign In
glass

glass

by fixed-width
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Rust

glass_a11y_snapshot_diff

Read-only

Generate lossless compact-outline revisions of accessibility snapshots to track GUI changes, recover full baselines, and verify edits, counts, and SHA-256 before advancing a caller-held revision.

Instructions

Experimental lossless compact-outline revisions for clients that reconstruct exact text. Every call reads fresh. Omit base_revision for full recovery; otherwise verify context, edits, byte/line counts and SHA-256 before advancing your caller-held baseline. Fetch and verify all output resources first. Partial observations retain their disclosures. IDs are immediate references from the latest read; revisions do not pin them. Full-profile only.

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": "glass_a11y_snapshot_diff"
  }
}

Input Schema

NameRequiredDescriptionDefault
max_nodesNoNode cap; omit for default, 0 removes only the node cap.
base_revisionNoCaller-held nonempty ASCII revision (at most 128 bytes); omit/null for full recovery.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.9.0

TDQS

B3.1/5.0
Behavior4/5

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

Annotations only cover readOnly/openWorld, but the description adds real behavior: every call reads fresh (no caching), IDs are immediate references that revisions do not pin, partial observations retain their disclosures, and output resources must be fetched and verified (context, edits, byte/line counts, SHA-256). These are substantive operational traits an agent could not derive from the annotations, though the phrasing is compressed to the point of ambiguity.

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

Conciseness3/5

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

Five short sentences with no filler, but they are telegraphic and jargon-dense, with the verification instructions piled on before the agent understands the core operation. It is compact without being front-loaded or well-sequenced.

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

Completeness2/5

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

This is a complex, stateful protocol tool with no output schema and no return-value explanation; "fetch and verify all output resources first" references resources the agent is never told how to enumerate. For a revision-diff tool with baseline/SHA-256 semantics, the definition leaves far too much to trial and error.

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 the schema already documents both parameters, and the description's "omit base_revision for full recovery" largely restates it. It adds the verification obligations around advancing a baseline but says nothing about max_nodes or the format of a valid revision beyond what the schema provides.

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

Purpose3/5

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

"Experimental lossless compact-outline revisions" gestures at diff/revision semantics but never states plainly what the tool returns (a diff? a revision token? a snapshot?). The verb is absent and nothing distinguishes it from siblings like glass_a11y_snapshot or glass_diff, which an agent could easily pick instead.

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?

"Omit base_revision for full recovery; otherwise verify ... before advancing your caller-held baseline" gives conditional parameter-level usage, and "Full-profile only" states a deployment constraint. However, it never says when to choose this over glass_a11y_snapshot or glass_diff, so tool selection remains inferred.

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