Skip to main content
Glama
delimit-ai

delimit

Official
by delimit-ai
OverviewSchemaRelated ServersScoreDiscussions
Python
Hybrid

Delimit Lint

delimit_lint

Compare two OpenAPI specs to detect breaking changes and policy violations, returning a pass/fail verdict for CI merge gates.

Instructions

Lint two OpenAPI specs for breaking changes and policy violations.

When to use: as the primary CI gate before merging API spec changes — combines diff + policy into a pass/fail verdict. When NOT to use: for raw change data (use delimit_diff) or quality scoring (delimit_spec_health).

Sibling contrast: delimit_diff returns changes only; delimit_diff_report renders HTML; this enforces policy.

Side effects: writes evidence on breaking findings; auto-chains semver classification and governance evaluation. dry_run=True suppresses evidence, notifications, and governance — returns violations + semver only.

Spec args accept local paths or http(s) URLs. URLs are fetched once into a tempfile (size cap, SSRF guard).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dry_runNoIf True, return violations + semver without side effects.
new_specYesPath or URL to the proposed spec.
old_specYesPath or URL to the baseline spec.
policy_fileNoOptional .delimit/policies.yml path.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed4 schema fields changedv4.7.9
    • changedInput schema / properties / dry_run / description
      Previous value: -"If True, return violations without side effects (no evidence, no chains)."New value: +"If True, return violations + semver without side effects."
    • changedInput schema / properties / new_spec / description
      Previous value: -"Path to the new (proposed) OpenAPI spec file."New value: +"Path or URL to the proposed spec."
    • changedInput schema / properties / old_spec / description
      Previous value: -"Path to the old (baseline) OpenAPI spec file."New value: +"Path or URL to the baseline spec."
    • changedInput schema / properties / policy_file / description
      Previous value: -"Optional path to a .delimit/policies.yml file."New value: +"Optional .delimit/policies.yml path."
  2. Changed4 schema fields changedv4.5.5
    • addedInput schema / properties / dry_run
      Added value: +{
+  "default": false,
+  "description": "If True, return violations without side effects (no evidence, no chains).",
+  "type": "boolean"
+}
    • addedInput schema / properties / new_spec / description
      Added value: +"Path to the new (proposed) OpenAPI spec file."
    • addedInput schema / properties / old_spec / description
      Added value: +"Path to the old (baseline) OpenAPI spec file."
    • addedInput schema / properties / policy_file / description
      Added value: +"Optional path to a .delimit/policies.yml file."
  3. First observedv0.1.0

TDQS

A4.9/5.0
Behavior5/5

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

The description goes well beyond the readOnlyHint/destructiveHint annotations by disclosing real side effects: writes evidence on breaking findings, auto-chains semver and governance evaluation, and explains that dry_run=True suppresses these behaviors. It also discloses non-obvious URL fetching behavior including tempfile use, size cap, and SSRF guard.

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 tightly organized with labeled sections: purpose, when to use, when not to use, sibling contrast, side effects, and argument behavior. Every sentence carries distinct operational information, with no filler or repetition of schema content.

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 tool that combines diff and policy evaluation, the description covers selection criteria, side effects, dry-run semantics, input formats, and safety behavior around URL fetching. Given the presence of an output schema, the description does not need to enumerate return fields, and everything an agent needs to invoke this tool correctly is present.

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?

The input schema already has 100% parameter coverage, so the baseline is 3. The description adds meaningful semantics beyond the schema by explaining that spec arguments accept local paths or HTTP(S) URLs and are fetched into a tempfile with safeguards, and by clarifying what dry_run=True actually returns versus suppresses.

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 opens with a specific verb and resource combination: 'Lint two OpenAPI specs for breaking changes and policy violations.' It also explicitly contrasts itself with delimit_diff and delimit_diff_report, making the tool's role unambiguous even within a large sibling list.

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?

The description provides explicit 'When to use' and 'When NOT to use' guidance, identifies the primary CI-gate context, and names concrete alternatives for raw diff data and quality scoring. This leaves no ambiguity about when an agent should select this tool over its siblings.

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