Skip to main content
Glama
Data.gov Semantic MCP

Data.gov Semantic MCP

by trevorspecht

Get Analysis Evidence

get_analysis_evidence
Read-only

Fetch saved analysis evidence—SQL, parameters, source hashes, definitions, and result rows—by ID to review or reuse it before an ephemeral app restart.

Instructions

Retrieve saved SQL, parameters, source hashes, definitions and result rows.

Evidence is public-data material accessible within the App permission boundary. It is stored locally: download it before an ephemeral App restart.

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": {
      "evidence_id": "<evidence_id>"
    },
    "name": "get_analysis_evidence"
  }
}

Input Schema

NameRequiredDescriptionDefault
evidence_idYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

The annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds real context beyond that: evidence is public-data material within the App permission boundary, and it is stored locally, so it must be downloaded before an ephemeral restart. That persistence and permission-boundary detail is genuinely useful, though it says nothing about whether retrieval fails, expires, or how large results are.

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?

The description is two short, front-loaded sentences: first the payload, then the persistence caveat. Nothing is wasted, though the pronoun "It" in the second sentence is slightly ambiguous about whether it refers to the evidence or the App.

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?

An output schema exists, so return values need not be re-explained, and the description still summarizes the payload while covering storage and permission behavior. The remaining gap is how to source a valid evidence_id, the one thing an agent must get right in order to call the tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There is only one parameter, and the schema description coverage is 0%; the schema constrains evidence_id only with a 32-character hex pattern. The description never explains what an evidence_id identifies or how an agent obtains one, so it fails to compensate for the coverage gap, which is a real risk for the sole required input.

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 definition gives a specific verb, "Retrieve", followed by a concrete resource, "evidence", and it then enumerates the exact payload: saved SQL, parameters, source hashes, definitions, and result rows. Because no sibling in the catalog retrieves a saved evidence artifact by ID, the scope is unambiguous without needing an explicit contrast sentence.

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 phrase "download it before an ephemeral App restart" implies when the tool should be invoked: before a session boundary, while the App is still alive. However, the description never states when not to use it, gives no prerequisites for obtaining an evidence_id, and points to no alternative path.

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