Skip to main content
Glama

delimit_audit

Audit code changes across three models using security, correctness, and governance lenses. Synthesizes agreements and disagreements to surface tradeoffs for high-confidence review.

Instructions

Cross-model code audit — 3 models, 3 lenses, synthesized (Pro).

When to use: for high-confidence review of a code change, where agreement across models is the signal and disagreements surface tradeoffs. When NOT to use: for raw multi-model debate (use delimit_deliberate) or single-model review (delimit_review).

Sibling contrast: delimit_review is single-prompt multi-model; delimit_deliberate is full debate; this is structured cross-lens audit (security / correctness / governance).

Side effects: gated by require_premium. Calls models via ai.cross_model_audit.audit. No ledger write — caller decides what to do with findings.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
targetNoFile path, git diff output, or code snippet to audit. Required.
target_typeNo"file" (default — reads file), "diff" (git diff text), or "snippet" (inline code).file
lensesNoComma-separated lenses — "security", "correctness", "governance". Empty = all three.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Behavior4/5

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

With no annotations provided, the description carries the full burden. It discloses side effects: gated by require_premium, calls ai.cross_model_audit.audit, and no ledger write. This is good coverage, though it could additionally mention output format or cost implications. Still, it provides significant transparency beyond minimal.

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 well-structured with clear headings (When to use, When NOT to use, Sibling contrast, Side effects). Every sentence serves a purpose, no redundancy, and it is front-loaded with the core purpose.

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?

Given the tool's complexity (3 params, output schema exists, no annotations), the description covers purpose, usage, alternatives, and key side effects. It does not explain the output format in plain language (but schema covers it) and omits potential costs, but the level of detail is sufficient for confident agent invocation. Minor room for improvement.

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?

All 3 parameters are described in the schema with 100% coverage. The description adds context about the three lenses (security, correctness, governance) and the cross-model nature, but does not materially extend the schema's semantics. Baseline 3 is appropriate.

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 clearly states the tool's verb (audit) and resource (code change), specifying it uses 3 models and 3 lenses (security, correctness, governance). It distinguishes itself from siblings delimit_review and delimit_deliberate by highlighting the cross-model structured audit approach.

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?

Explicitly provides 'When to use' and 'When NOT to use' with concrete alternatives (delimit_deliberate for debate, delimit_review for single-model review). The 'Sibling contrast' section further clarifies the differentiation, leaving no ambiguity for the agent.

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/delimit-ai/delimit-mcp-server'

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