Skip to main content
Glama

Get Evidence Bundle

get_evidence_bundle
Read-onlyIdempotent

Retrieve Evidence records and residual unknowns as a canonical bundle, or list summaries to discover records without payload transfer. Filter summaries by evidence ID, operation, or procedure address.

Instructions

Return every retained Evidence record and residual unknown as a complete canonical bundle by default. detail=summary discovers retained records without copying or transferring their payloads; optionally filter by exact Evidence ID, operation, target SHA-256, analysis-profile digest or canonical native procedure address. Metadata distinguishes complete record retention from native value-flow truncation or unavailable/unknown coverage. Use a discovered evidence_id with inspect_analysis_view without restarting a provider. Filters apply only to summary delivery.

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": {
      "detail": "summary",
      "filters": {
        "operation": "analyze_function",
        "procedure_address": "0x1000"
      }
    },
    "name": "get_evidence_bundle"
  }
}

Input Schema

NameRequiredDescriptionDefault
detailNo
filtersNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and closed-world scope, so the safety profile is covered. The description adds genuinely useful behavior: summary mode avoids transferring payloads, metadata signals truncation vs. complete retention, and 'Filters apply only to summary delivery' is a non-obvious constraint. It does not say anything about bundle size, pagination, or what a complete-mode response looks like, which keeps this at a 3.

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?

Five sentences, front-loaded with the default behavior and the mode distinction before the filters and the handoff tip. Every sentence carries information, though the density of domain jargon ('residual unknown', 'canonical native procedure address') makes a single read-through costly.

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 two-parameter read tool with no output schema, the description covers mode selection, filter scope, and return-metadata semantics adequately. It leaves gaps around output shape for complete delivery and expected size/cost of retrieving full payloads, which matter given the description itself warns about payload transfer.

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?

With schema description coverage at 0%, the description carries the burden and mostly succeeds: it defines the two detail modes, enumerates all five filter keys (evidence ID, operation, target SHA-256, analysis-profile digest, procedure address), and states the crucial constraint that filters only apply to summary delivery — something the schema never conveys. It does not explain filter combination semantics (AND/OR) or what an invalid evidence_id pattern produces.

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?

States a specific verb and resource ('Return every retained Evidence record and residual unknown as a complete canonical bundle') and immediately contrasts the default with the detail=summary mode, which lets an agent pick a delivery mode without opening the schema. It stops short of explicitly naming sibling tools like export_evidence_bundle to draw the boundary, though 'without copying or transferring their payloads' gestures at it.

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

Usage Guidelines4/5

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

Gives concrete routing guidance: use the default for a full bundle, use detail=summary to discover records cheaply, then feed a discovered evidence_id into inspect_analysis_view 'without restarting a provider'. There is no explicit when-not or named-alternative exclusion, but the workflow context is clear enough to select correctly.

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