Skip to main content
Glama

create_evidence_bundle

Creates a new in-progress evidence bundle for a task and primary workspace, optionally including additional monorepo packages and metadata for traceable agent work.

Instructions

Creates a new evidence bundle for a task and primary workspace (with optional additional monorepo packages) with in_progress status.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "task": "<task>",
      "workspacePath": "<workspacePath>"
    },
    "name": "create_evidence_bundle"
  }
}

Input Schema

NameRequiredDescriptionDefault
taskYesThe task or objective being addressed by the agent.
metadataNoOptional key-value metadata.
workspacePathYesPath to the primary workspace root directory.
additionalWorkspacesNoOptional map of named additional workspaces/packages (e.g. { "frontend": "./packages/frontend" }).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.4.0
    • addedInput schema / properties / additionalWorkspaces
      Added value: +{
      +  "additionalProperties": {
      +    "type": "string"
      +  },
      +  "description": "Optional map of named additional workspaces/packages (e.g. { \"frontend\": \"./packages/frontend\" }).",
      +  "propertyNames": {
      +    "type": "string"
      +  },
      +  "type": "object"
      +}
    • changedInput schema / properties / workspacePath / description
      Previous value: -"Path to the workspace root directory."New value: +"Path to the primary workspace root directory."
  2. First observedv0.1.0

TDQS

B3.2/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full disclosure burden; it does add one genuinely useful behavioral fact — the bundle is created with in_progress status. It says nothing about prerequisite auth/registration, idempotency or failure if a bundle already exists, or whether the new bundle is mutable afterwards.

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?

One front-loaded sentence with no filler; the parenthetical correctly marks additionalWorkspaces as optional. It is dense but every clause maps to real schema content, so nothing needs trimming.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a creation tool with no annotations and no output schema, the definition covers inputs adequately but leaves the return value unexplained — an agent does not learn whether a bundle identifier is returned for use in downstream endorse/sign/verify calls. That omission matters given the clear create-then-sign workflow implied by siblings.

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 task, workspacePath, metadata, and additionalWorkspaces are already documented in the schema. The description corroborates the workspace/package structure but adds no new semantics such as path format expectations or how named additional workspaces relate to the primary one.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ("Creates a new evidence bundle") plus its scoping (task, primary workspace, optional additional monorepo packages). It does not distinguish this tool from sibling creation/capture tools (capture_ast_evidence, capture_git_evidence, snapshot_files), so an agent must infer the boundary itself.

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

Usage Guidelines2/5

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

There is no guidance on when to call this versus the other bundle-related siblings (endorse_/sign_/notarize_/verify_evidence_bundle) or the capture_* tools. The only implied usage is that a bundle must exist before it can be endorsed or signed, which the agent has to deduce from sibling names rather than from this text.

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