Skip to main content
Glama

Review a board's design

review_board

Use when the user asks whether a BoardRepo board they can review is correct or has problems, or asks for a design review. Returns BoardRepo's design-review findings for the selected version, each with severity, confidence and evidence, plus exact counts and what the review did NOT check. Requires board review permission; unrelated public boards are excluded. On the latest version, a first call on an unreviewed board starts a review job (status "running"; call again shortly), and refresh re-runs it while returning the stored findings. Findings are machine-generated hypotheses: confirm them with get_findings and verify_claim before repeating them as fact, and weight them by confidence ("deterministic" means the arithmetic is certain GIVEN a correct netlist, not that it is a real defect). get_checks returns KiCad's DRC and ERC.

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": {
      "board": "<board>"
    },
    "name": "review_board"
  }
}

Input Schema

NameRequiredDescriptionDefault
boardYesA personal board, or an organisation board with read:org consent and check permission: handle/slug or a boardrepo.com URL. Discover it with list_my_boards; do not guess one.
stageNoOptional. Which review stage to report. schematic: symbol, connectivity and part-value checks. layout: placement and routing. pre_fab: manufacturability. bring_up: first-power-on. Omit for every stage.
cursorNoOpaque pagination cursor from a previous call; pass to fetch the next page of findings.
refreshNoRe-run the review even when a current result exists. Only pass this when the board changed or the user explicitly asks for a re-run; a normal call reuses the stored result.
versionNoWhich saved version to read: a version number (3 or "v3"), a versionId from list_board_versions, "latest", or a release tag such as "rev-A". Omit for the latest version. Results echo the version they read; pass its id back to stay on it.
detectorNoOptional. Only findings from this detector, exactly as returned in a previous finding's detector field. Do not guess one.
severityNoOptional minimum severity: "error" returns only errors, "warning" returns errors and warnings. Counts for every severity are always returned regardless.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added
  2. Removed
  3. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Adds substantial context beyond the annotations: the first call on an unreviewed latest version starts a job and returns status 'running' with a retry instruction, refresh re-runs but still returns stored findings, and results include counts and what was NOT checked. It also discloses the epistemic caveat that findings are machine-generated hypotheses and that 'deterministic' means certain arithmetic given a correct netlist. This is consistent with readOnlyHint=false (a job may be started) and destructiveHint=false.

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?

Front-loaded with the usage trigger and the return summary before caveats, and every sentence carries information (job semantics, permissions, sibling routing, confidence caveat). It is dense and long for a description, but no sentence is filler.

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

Completeness5/5

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

Despite job-start semantics and a permission gate, the description covers failure-adjacent context, async behavior, re-check guidance and caveats about the findings' reliability. With a full schema and an output schema present, nothing an agent needs to call it correctly is missing.

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% and the schema itself already explains refresh, version, detector, severity minimum and cursor semantics, so the description need not duplicate them. The description adds only indirect parameter meaning ('call again shortly' after a running job; case sensitivity via 'refresh re-runs it'), which is close to baseline when the schema does the heavy lifting.

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 ('Returns BoardRepo's design-review findings for the selected version') plus the trigger condition ('whether a board is correct or has problems'). It explicitly separates itself from get_checks ('KiCad's DRC and ERC') and get_findings, so an agent can pick the right tool without opening schemas.

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

Usage Guidelines5/5

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

Gives explicit when-to-use ('user asks whether a board ... is correct or has problems, or asks for a design review'), scope exclusions ('unrelated public boards are excluded'), a permission prerequisite, and named follow-on alternatives (get_findings, verify_claim, get_checks).

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