Skip to main content
Glama

review_and_remediate

Assess code for security, standards, readiness, and sustainability; automatically apply fixes, run tests to confirm they work, and return a scorecard, diff, and updated code.

Instructions

Review code across security, standards, readiness, and sustainability; automatically fix the issues; verify the fix by running its tests; and return the findings, a per-dimension scorecard over all rules (passes included, for coverage attestation), the remediated code, a diff, citations, and a metrics-style summary.

Args: code: the source code to review. language: the source language (default: python). tests: optional — the code's test suite if it lives in a separate file. Provide it so the review runs the tests (they should import the code as solution, e.g. from solution import ...) and doesn't false-positive on "no tests detected". tests_dir: optional — path to the code's test directory. Confirms tests are present (RDY-03) WITHOUT running them; this is how coverage is attested in detect-only mode (CODEPECKER_REMEDIATE=false), which skips test execution. support_files: optional {filename: source} of sibling modules the code (or its tests) imports — e.g. {"crypto.py": "...", "db.py": "..."}. They're written into the sandbox next to the code so a local from crypto import ... resolves instead of crashing test collection. Local files only; nothing is installed from a package index.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
codeYes
testsNo
languageNopython
tests_dirNo
support_filesNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Behavior5/5

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

With no annotations, the description fully carries the transparency burden. It discloses automatic fixing, test execution, sandbox writing of support files, the non-execution of tests_dir tests, and environment-variable-driven mode changes. No contradictions detected.

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?

The description is long but appropriately so for a complex tool. The opening paragraph front-loads the overall pipeline, and the Args section uses a clear bulleted structure. Every sentence adds behavioral or parameter value without repeating schema defaults.

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?

For a high-complexity tool, the description covers the full workflow, return artifact categories, mode-specific behavior, and sandbox limitations. The output schema handles return-type details, while the description supplies usage context and edge-case guidance, making it complete enough for an agent to invoke correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, but the description compensates thoroughly. Each parameter gets practical context: language default, test import convention (as `solution`), tests_dir RDY-03 attestation, support_files usage with an example, and the 'local files only' constraint. This is far more than the schema alone provides.

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?

The description states a specific, multi-step purpose: review code across security, standards, readiness, and sustainability; automatically fix issues; verify via tests; and return findings, scorecard, remediated code, diff, citations, and metrics. This goes well beyond a vague verb+noun and clearly delineates the tool's end-to-end scope.

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?

The description gives clear context on when to supply optional inputs (tests, tests_dir, support_files) and how detect-only mode (CODEPECKER_REMEDIATE=false) changes behavior. Since there are no sibling tools, explicit alternatives are unnecessary, but it stops short of explicitly stating when not to use the tool.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/Abdul4code/CodePecker'

If you have feedback or need assistance with the MCP directory API, please join our Discord server