Skip to main content
Glama

capture_ast_evidence

Extracts AST symbols, signatures, and semantic diffs from target source files, including Git HEAD comparisons and breaking-change detection, to store structured evidence in a bundle.

Instructions

Extracts AST symbols, signatures, and computes semantic diffs (with Git HEAD comparison and breaking change detection) for target source files.

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": {
      "bundleId": "<bundleId>",
      "files": "<files>"
    },
    "name": "capture_ast_evidence"
  }
}

Input Schema

NameRequiredDescriptionDefault
filesYesArray of relative or absolute file paths to analyze within workspace.
bundleIdYesThe unique identifier of the evidence bundle.
workspaceNameNoOptional name of the workspace for monorepo packages (defaults to "root").
workspacePathNoOptional workspace root directory to locate the bundle.
compareWithGitHeadNoWhether to compare symbols against Git HEAD to detect changes and breaking changes.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.4.0

TDQS

B3.2/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it does disclose a meaningful behavioral trait: comparison against Git HEAD, which implies a Git repository context, plus breaking-change detection that can be toggled off via a parameter. However, it never states that results are persisted into the identified bundle, whether existing evidence is overwritten, or what happens when a file path is invalid, leaving the mutation profile opaque.

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?

A single compact sentence that front-loads the primary action and nests the optional behaviors in a parenthetical, so the main function is read first. The parenthetical is slightly dense but every clause carries information.

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

Completeness3/5

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

For a five-parameter tool with no annotations and no output schema, the description covers the main operation and its Git-HEAD behavior but omits what the caller receives, whether evidence is stored in the bundle, and failure conditions. Adequate to select the tool, insufficient to predict its side effects.

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%, so every parameter including compareWithGitHead, workspaceName, and bundleId is already documented in the schema. The description adds only the general notion of "target source files" and does not clarify path resolution rules or how workspacePath interacts with relative file paths, so the baseline of 3 applies.

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 specific verb-plus-resource combination ("Extracts AST symbols, signatures") and adds what is computed (semantic diffs, breaking change detection), which distinguishes it from capture_git_evidence and capture_sbom_evidence by subject matter. It stops short of explicitly naming a sibling or stating its scope boundary, so an agent must infer the split from the evidence type alone.

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

Usage Guidelines2/5

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

There is no explicit when-to-use or when-not-to-use guidance, and no alternative tool is named. The phrase "for target source files" implies the domain, but the agent gets no signal about prerequisites such as whether the bundleId must reference an already-created bundle, or when to prefer a different capture tool.

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