Skip to main content
Glama
delimit-ai

delimit

Official
by delimit-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Delimit Evidence Collect

delimit_evidence_collect

Create verifiable evidence bundles after deploys, audits, or test runs to preserve proof for later attestation. Solves governance compliance by capturing gate-event artifacts in a replayable format.

Instructions

Collect evidence artifacts for governance (Pro).

When to use: after a deploy, security audit, test run, or other gate event — to capture an evidence bundle that delimit_evidence_verify can later attest. When NOT to use: to verify an existing bundle (use delimit_evidence_verify) or query the contract ledger (delimit_ledger).

Sibling contrast: delimit_evidence_verify verifies; delimit_ledger queries the chain; this collects new evidence.

Side effects: gated by require_premium. Writes a new evidence bundle via backends.repo_bridge.evidence_collect.

Prerequisite: requires Delimit Pro. An unlicensed call returns {"error": ..., "upgrade": "https://delimit.ai/pricing"} without running.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
targetNoRepository or task path. Default "." (cwd)..
asset_metaNoOptional JSON string with asset provenance metadata (for evidence_type='asset').
evidence_typeNoType of evidence — e.g. "deploy", "security", "test", "audit". Stored in bundle metadata. Empty = generic.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv4.7.9
    • addedInput schema / properties / asset_meta
      Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Optional JSON string with asset provenance metadata (for evidence_type='asset')."
+}
    • changedInput schema / properties / evidence_type / description
      Previous value: -"Type of evidence (e.g. \"deploy\", \"security\", \"test\", \"audit\"). Stored in bundle metadata."New value: +"Type of evidence — e.g. \"deploy\", \"security\", \"test\", \"audit\". Stored in bundle metadata. Empty = generic."
    • changedInput schema / properties / target / description
      Previous value: -"Repository or task path."New value: +"Repository or task path. Default \".\" (cwd)."
  2. Changed2 schema fields changedv4.5.5
    • addedInput schema / properties / evidence_type
      Added value: +{
+  "default": "",
+  "description": "Type of evidence (e.g. \"deploy\", \"security\", \"test\", \"audit\"). Stored in bundle metadata.",
+  "type": "string"
+}
    • addedInput schema / properties / target / description
      Added value: +"Repository or task path."
  3. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only carry readOnlyHint=false and destructiveHint=false, so the description carries the behavioral burden and meets it: it discloses the write side effect ('Writes a new evidence bundle via backends.repo_bridge.evidence_collect'), the licensing gate (require_premium / Delimit Pro), and the unlicensed failure mode (returns an error with an upgrade URL without running). No annotation contradiction — readOnlyHint=false is consistent with the write behavior.

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?

Well-structured with labeled sections (When to use, When NOT to use, Sibling contrast, Side effects, Prerequisite) and a front-loaded purpose. Slightly repetitive — the sibling contrast largely restates the when-NOT-to-use section — but every section still earns its place given the licensing and side-effect nuances.

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 with an existing output schema and 100% schema parameter coverage, this description is complete: it covers trigger conditions, exclusions, named alternatives, side effects, prerequisite licensing, and the exact unlicensed failure behavior. There are no meaningful gaps for an agent deciding whether and how to call it.

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%, so the baseline is 3 and the schema already documents all three parameters. The description adds indirect contextual value by linking gate events (deploy, security audit, test run) to the evidence_type examples, but it does not materially explain parameter semantics beyond what the schema 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?

Opens with a specific verb+resource: 'Collect evidence artifacts for governance (Pro).' The sibling contrast section explicitly differentiates it from delimit_evidence_verify (verifies) and delimit_ledger (queries the chain), so an agent can distinguish it from nearby tools 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?

Provides explicit when-to-use conditions ('after a deploy, security audit, test run, or other gate event'), an explicit when-NOT-to-use with named alternatives (delimit_evidence_verify, delimit_ledger), and a sibling contrast. Nothing is left to inference.

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

Deploy Server

Other Tools