Skip to main content
Glama

MemBrowse

Compare builds

compare_builds
Read-only

Compare two builds of a target. Always returns each region's old and new size; 'level' adds the changed sections, source files or symbols, sorted by size of change. Without 'base', the head is compared with the build it was compared with when it was uploaded: for a pull request's head commit that is the tip of the PR's base branch, so the result is the whole PR; for a pushed commit it is the branch's previous build, so the result is what that one commit did. With 'base_target', the base is a build of another target instead, to see which target already does without a symbol.

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": {
      "project": "<project>",
      "target": "<target>"
    },
    "name": "compare_builds"
  }
}

Input Schema

NameRequiredDescriptionDefault
baseNoThe older build, in the same forms. Default: the build 'head' was compared with when it was uploaded (for a pull request, the tip of its base branch); with 'base_target', the head of that target's default branch.
headNoThe newer build: a full commit SHA, a SHA prefix (7+ characters), or a branch or tag name. Default: the head of the default branch. For a pull request, its head commit SHA.
levelNoDetail to return (default 'regions'). 'symbols' and 'files' load full reports and are slower.
limitNoMaximum rows to return (default 50, max 200).
regionNoOnly this memory region, e.g. FLASH or RAM.
targetYesTarget name (see list_targets).
projectYesThe project: a public project's GitHub 'owner/repo' (no API key needed), or, with an API key, a project id or name from list_projects.
sectionNoOnly this section, e.g. .text (sections and symbols levels).
base_targetNoCompare with this other target of the project ('base' then names its build).
name_containsNoOnly sections, files or symbols whose name contains this text (case-insensitive).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior3/5

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

Annotations already cover the safety profile (readOnly, non-destructive, closed-world), and the description adds the nontrivial default-resolution behavior: without 'base', a PR head resolves to the base-branch tip while a pushed commit resolves to the branch's previous build, which materially changes what the result means. The performance note for 'files'/'symbols' lives in the schema rather than the description, so the extra context here is real but modest.

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?

Front-loads the core action and return shape, then layers defaults and the base_target variant in dependency order. Dense but every clause carries information; nothing is redundant with the title or schema.

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?

Ten parameters, no output schema, so the description must carry the return-value burden — and it does, stating what is always returned and what each 'level' adds. A short note on ordering of rows beyond 'sorted by size of change' would close the remaining gap.

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, but the description goes beyond the schema's terse 'base' default by spelling out what that default implies semantically for PRs versus pushed commits ('the result is the whole PR' vs 'what that one commit did'). That added interpretation of parameter omission is genuine value.

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?

States a specific verb and resource ('Compare two builds of a target') and immediately specifies the return contract ('always returns each region's old and new size'). This is enough to distinguish it from siblings like get_commit_summary or get_memory_history without opening a schema.

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?

Explains the selection logic between the three modes: omit 'base' for the implicit comparison, supply 'base' for explicit builds, or use 'base_target' to compare against another target — including the motivating case ('to see which target already does without a symbol'). It lacks explicit exclusion guidance versus sibling tools, but the internal mode routing is clear and actionable.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources