Skip to main content
Glama
delimit-ai

delimit

Official
by delimit-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

Delimit Evidence Verify

delimit_evidence_verify

Confirm an evidence bundle's hash chain integrity to prove it hasn't been altered during replay or audit.

Instructions

Verify the integrity of an evidence bundle (Pro).

When to use: to attest that a previously-collected evidence bundle has not been tampered with — typical use is during replay or audit. When NOT to use: to capture new evidence (use delimit_evidence_collect) or to query the contract ledger (delimit_ledger).

Sibling contrast: delimit_evidence_collect captures; this verifies a captured bundle's hash chain integrity.

Side effects: read-only on the evidence store; gated by require_premium. Calls backends.repo_bridge.evidence_verify.

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

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
bundle_idNoEvidence bundle id. Either this or bundle_path must be provided.
bundle_pathNoPath to a bundle file on disk. Either this or bundle_id must be provided.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv4.7.9
    • changedInput schema / properties / bundle_id / description
      Previous value: -"Evidence bundle ID to verify."New value: +"Evidence bundle id. Either this or bundle_path must be provided."
    • changedInput schema / properties / bundle_path / description
      Previous value: -"Path to evidence bundle file."New value: +"Path to a bundle file on disk. Either this or bundle_id must be provided."
  2. Changed2 schema fields changedv4.5.5
    • addedInput schema / properties / bundle_id / description
      Added value: +"Evidence bundle ID to verify."
    • addedInput schema / properties / bundle_path / description
      Added value: +"Path to evidence bundle file."
  3. First observedv0.1.0

TDQS

A3.9/5.0
Behavior1/5

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

The description provides unusually rich behavioral detail: read-only side effects, gating by require_premium, the backend call target, and the unlicensed error payload. However, it directly contradicts the annotations, which set readOnlyHint to false while the description claims the tool is read-only; per rubric this is a contradiction, so score 1.

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 compact yet sectioned: purpose, when/when-not, sibling contrast, side effects, and prerequisite. The implementation detail about backends.repo_bridge.evidence_verify is slightly superfluous but does not hurt. Front-loading is excellent.

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?

Given the output schema exists and the input schema covers both parameters, the description supplies all selection and invocation context: use case, exclusions, preconditions, side effects, and failure mode. An agent can correctly decide when to call and what to expect from an unlicensed call.

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?

Both parameters are fully described in the schema (100% coverage), so the description does not need to add much. It adds the context that the bundle was previously collected, but the schema already covers the mutual exclusivity of bundle_id and bundle_path. 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 opens with a specific verb and resource: 'Verify the integrity of an evidence bundle (Pro).' It explains what verification means (attesting the bundle has not been tampered with) and distinguishes itself from delimit_evidence_collect in the sibling contrast. This is a clear, unambiguous purpose.

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?

It explicitly states when to use (replay or audit) and when NOT to use, naming both delimit_evidence_collect and delimit_ledger as alternatives. The sibling contrast reinforces the boundary, leaving no ambiguity about tool selection.

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