Skip to main content
Glama
Datris MCP Server

Datris MCP Server

get_incident_evidence

Retrieve deterministic evidence for a recovery-agent incident: baseline and post-fix profiles, diffs, blast radius, threshold checks, and verdict, computed by platform code without sensitive values.

Instructions

Read the deterministic evidence the platform computed for one recovery-agent incident: the baseline profile of the last successful run before it broke, the profile of the real run after the fix, the diff between them (columns added or removed, type changes, record-count delta, null-rate deltas, distribution shift), the blast radius (downstream pipelines, datasets and catalog tables, and which agent identities queried them when reads are audited), the thresholds in force, each threshold check, and the verdict (pending | pass | fail | needs-human). Computed by platform code, never by a model; values from protected or sensitive-looking columns are never included. Returns an error when the incident has no evidence.

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": {
      "incident_id": "<incident_id>"
    },
    "name": "get_incident_evidence"
  }
}

Input Schema

NameRequiredDescriptionDefault
incident_idYesThe incident id (inc_…).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and mostly succeeds: it discloses provenance ("Computed by platform code, never by a model"), a privacy guarantee (protected or sensitive-looking column values are never included), and the failure mode (error when no evidence exists). It omits things like response size, latency or whether evidence can be partially missing/stale for an in-flight incident.

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?

Front-loaded with the verb and resource, and the long enumeration of returned artifacts earns its length because there is no output schema. The clause ordering is logical (contents, then provenance, then privacy, then error), though the payload list is dense and could be split for readability.

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 single-parameter read tool with no output schema, the description substitutes well for a return-value spec by enumerating every artifact returned, and it covers the key edge case of an incident lacking evidence. Nothing an agent needs to decide to call it or interpret the result is missing.

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% for the single incident_id parameter, which already documents the inc_… format, so the baseline is 3. The description adds no extra meaning about the id beyond what the schema states.

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 ("Read") plus the exact resource (deterministic evidence for one recovery-agent incident) and then enumerates the payload: baseline profile, post-fix profile, diff dimensions, blast radius, thresholds and verdict. That is enough to separate it from the sibling get_incident, which presumably returns incident metadata rather than computed evidence.

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?

Usage is implied by the scoping phrase "for one recovery-agent incident" and by the error note "Returns an error when the incident has no evidence," which tells the agent when the call fails. However, it never explicitly says when to prefer this over get_incident, get_provenance or get_lineage, nor any precondition beyond having an incident id.

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