Skip to main content
Glama

code_review_architecture

Read-onlyIdempotent

Scans pasted source code for architecture and security risks such as hardcoded secrets, insecure calls, SQL concatenation, disabled TLS, and missing timeouts.

Instructions

Heuristic architecture and security scan of source code pasted as text (any language): secrets, insecure calls, SQL built by concatenation, disabled TLS, hardcoded endpoints, missing timeouts and retry hazards. Not a linter or SAST replacement.

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": {
      "code": "<code>"
    },
    "name": "code_review_architecture"
  }
}

Input Schema

NameRequiredDescriptionDefault
codeYes
filenameNosnippet
languageNoauto

Output Schema

NameRequiredDescriptionDefault
kindNo
metricsNo
sourcesNo
summaryNo
filenameNo
findingsNo
languageNo
truncatedNo
validatedNo
limitationNo
limitationsNo
architectureQuestionsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.5.0
    • changedInput schema / required
      Previous value: -[
      -  "filename",
      -  "language",
      -  "code"
      -]New value: +[
      +  "code"
      +]
  2. First observedv0.4.1

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), so the description's job is to add fidelity context, which it does by calling the scan 'heuristic' and disclaiming SAST/linter equivalence — telling the agent results are indicative, not exhaustive. It stops short of saying whether findings include severity, line numbers, or how the 60k character cap behaves, but the core behavioral caveat is disclosed.

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?

One dense sentence front-loads what is scanned and its input mode, followed by a one-line limitation — no preamble or filler. The finding list is long but each item is a concrete check that earns its place; a marginally tighter grouping would be the only improvement.

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?

An output schema exists, so return-value detail is unnecessary, and the description supplies the input mode, scope, and a limitation statement appropriate for a read-only heuristic scanner. The remaining gaps — how the filename affects reporting and what happens near the character cap — are minor against the schema's maxLength and enum coverage.

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 0%, so the description must carry the parameter burden. It explains that 'code' is the pasted source and that any language is accepted, which implicitly justifies the 'auto' default on 'language', but 'filename' (default 'snippet') is never explained and the enum values and size limit are left entirely to the schema.

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 ('heuristic architecture and security scan of source code pasted as text') and then enumerates the exact classes of findings: secrets, insecure calls, SQL built by concatenation, disabled TLS, hardcoded endpoints, missing timeouts and retry hazards. That enumeration, plus 'pasted as text (any language)', distinguishes it from sibling review tools that target manifests, policies, or IaC files rather than raw source.

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?

The closing line 'Not a linter or SAST replacement' is a real when-not signal and sets expectations for a quick heuristic pass rather than a definitive audit. However, no sibling alternative is named (e.g. dependency_manifest_review, iam_policy_review, terraform_plan_review) and there is no explicit statement of the intake condition beyond 'pasted as text', so the agent must infer when this beats another review tool.

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