Skip to main content
Glama

verify

Checks a zipped or extracted bundle against its manifest before building, reporting missing or changed files, missing assets, font-face status, and a non-blocking preflight findings list.

Instructions

Check a bundle, zipped or extracted, against its manifest before building from it: verified, missing and changed files, the bundle's missing assets, and the font faces the visible text uses (with node ids). Each font face is looked up by its name table in this machine's user and system font folders and in fonts (a project font folder): status local_file with localFiles {path, matchedBy, inProject} when a file is found (WOFF/WOFF2 by file name only), else unverified; a match inside fonts also carries a ready fontFace @font-face (src relative to fonts, font-display swap; licensing is the user's call, nothing is copied). local_file never shows the browser loads the face: confirm each in the running project with document.fonts.load, and check browser delivery of assets there. findings gathers these checks with the bundle's unresolved variables, truncated state inventory, render limitations and unemitted semantics into one handoff preflight list, each with node ids, evidence, impact and next action. Reports without blocking; no design file is read.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "bundle": "<bundle>"
    },
    "name": "verify"
  }
}

Input Schema

NameRequiredDescriptionDefault
fontsNoabsolute path of a project directory of font files (subfolders included) searched before the system folders; must be inside the configured roots
bundleYespath to a bundle .zip or the directory it was extracted to

Output Schema

NameRequiredDescriptionDefault
pathYes
filesYesverified count; missing paths; changed entries with expected and actual size/sha256 (actual null when larger than declared, unreadable, with error, or not a regular file inside the bundle); invalid manifest paths
fontsYesfamily, style, weight, postScriptName, nodeIds, status (local_file or unverified; neither shows the browser loads the face), localFiles (up to 3 {path, matchedBy postScriptName|family+style|filename, inProject}) and, for a match inside fonts, fontFace: an @font-face snippet
findingsYeshandoff preflight, missing inputs first: category (integrity, asset, variable, scope, render, semantics, font), status (missing, unsupported or unverified), source file, nodeIds (at most 20, none over 1 KiB) and nodeCount, evidence, impact and action; at most 500 entries and 1 MiB
truncatedYesoriginal length of each other list cut to stay within the reply budget (files.missing, files.changed, files.invalid, missingAssets, fonts); empty when nothing was cut
fontLookupYessearched folders, filesRead (font files whose names were read) and truncated (a file, entry or byte budget stopped the lookup, so an unverified face may still have a file)
unverifiedYes
missingAssetsYesmissing-assets.json entries
findingsSummaryYesscope (bundle root nodeId and name), total, returned, truncated, counts per category/status, unexamined metadata files, semanticsCoverage (the handoff inventory's coverage) and the coverage the findings do not establish

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.11.3
    • addedInput schema / properties / fonts
      Added value: +{
      +  "description": "absolute path of a project directory of font files (subfolders included) searched before the system folders; must be inside the configured roots",
      +  "minLength": 1,
      +  "type": "string"
      +}
    • addedOutput schema / properties / fontLookup
      Added value: +{
      +  "description": "searched folders, filesRead (font files whose names were read) and truncated (a file, entry or byte budget stopped the lookup, so an unverified face may still have a file)",
      +  "type": "object"
      +}
    • changedOutput schema / properties / fonts / description
      Previous value: -"family, style, weight, postScriptName, nodeIds and status, always unverified"New value: +"family, style, weight, postScriptName, nodeIds, status (local_file or unverified; neither shows the browser loads the face), localFiles (up to 3 {path, matchedBy postScriptName|family+style|filename, inProject}) and, for a match inside fonts, fontFace: an @font-face snippet"
    • changedOutput schema / required
      Previous value: -[
      -  "path",
      -  "files",
      -  "missingAssets",
      -  "fonts",
      -  "unverified",
      -  "findings",
      -  "findingsSummary",
      -  "truncated"
      -]New value: +[
      +  "path",
      +  "files",
      +  "missingAssets",
      +  "fonts",
      +  "fontLookup",
      +  "unverified",
      +  "findings",
      +  "findingsSummary",
      +  "truncated"
      +]
  2. Addedv0.9.3

TDQS

A3.6/5.0
Behavior4/5

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

With no annotations, the description carries the burden well: it states it is non-blocking, reads no design file, copies nothing (licensing is the user's call), and clarifies that local_file only reflects a font file found on disk, not browser delivery. These are meaningful behavioral disclosures beyond the schema; only rate limits/performance are unaddressed.

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?

The core purpose is front-loaded, but the body is a single compressed run-on with nested clauses (font matching, findings aggregation) that is hard to parse. Most content is substantive, but the wall-of-text structure reduces readability.

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 complex verifier with an output schema, the description is largely complete: it explains manifest-check outcomes, font-face resolution statuses (local_file vs unverified), and what findings aggregates. Minor gaps exist around what 'ready fontFace' means in practice, but overall it is sufficient to call correctly.

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 description coverage is 100% (both fonts and bundle are documented, including the roots constraint), so the schema does the heavy lifting. The description adds only marginal color, noting fonts is 'a project font folder' whose matches produce ready @font-face output, giving baseline 3.

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?

The description uses a clear verb+resource (check a bundle against its manifest) and enumerates exactly what is reported: verified, missing and changed files, missing assets, font-face usage with node ids. It doesn't name a specific differentiating sibling, but the purpose is unambiguous and distinguishable from build-oriented tools like bundle/export.

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?

'before building from it' gives a timing/context cue, and 'Reports without blocking; no design file is read' implies a safe preflight use. However, it never explicitly names alternatives (e.g., bundle, inspect) or states when NOT to use it, so guidance is implied rather than spelled out.

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