Skip to main content
Glama

Export Evidence Bundle

export_evidence_bundle
DestructiveIdempotent

Atomically write a session's deterministic Evidence bundle to an absolute local path, with byte-stable record and manifest ordering plus an overwrite flag for existing files.

Instructions

Atomically write the session's deterministic Evidence bundle to the requested local path. Existing files require overwrite: true; records and manifests use canonical byte-stable ordering.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "path": "/tmp/evidence.json",
      "overwrite": false
    },
    "name": "export_evidence_bundle"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYesAbsolute local filesystem path for the exported evidence bundle; relative paths are rejected.
overwriteNoWhether an existing destination may be replaced.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare destructive=true, idempotent=true and readOnly=false, so the description is not the sole source of the safety profile. It still adds substantive behavior the annotations do not: the write is atomic, existing files require overwrite: true, and records/manifests use canonical byte-stable ordering (i.e., repeat exports are deterministic).

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?

Two compact sentences with no filler; the operation and destination are front-loaded, with the precondition and determinism guarantee following. Nothing repeats the schema verbatim.

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?

For a two-parameter, non-open-world export with annotations covering mutability, the description covers destination rules, overwrite semantics and determinism. The only gap is whether the call returns anything (path, hash, manifest) since no output schema exists, but that is minor for an export-to-disk tool.

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?

Schema coverage is 100%, so baseline is 3. The description goes further by linking the overwrite flag to the concrete failure condition ('existing files require overwrite: true'), which is a behavioral constraint the schema's 'Whether an existing destination may be replaced' does not convey.

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?

States a specific verb ('write/export') plus resource ('session's deterministic Evidence bundle') and destination ('requested local path'). The atomic single-operation framing clearly separates it from get_evidence_bundle (retrieval) and import_evidence_bundle (inbound).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The overwrite precondition is stated, which effectively tells the agent when a call will fail without it. However, there is no explicit 'use this instead of get_evidence_bundle when...' routing guidance, so the user must infer the read-vs-write split from sibling names.

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