Skip to main content
Glama

NS Pros MCP Gateway

ntsb-investigations__research_row

Claygent-style per-row research: answer ONE question about ONE company and return a JSON object matching your output_schema, with every field wrapped in its own evidence, {value, evidence_url, quote, status}. status is NEVER self-reported by the model: "found" means this code independently verified the model's quote is a VERBATIM substring of text actually fetched; "inferred" means a value was given but the quote could not be verified; "not_established" means no source answered the field, and it

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": {
      "entity": {
        "name": "Stripe",
        "domain": "stripe.com"
      },
      "sources": "web",
      "max_cost": 0.02,
      "question": "Does this company sell to healthcare, and who is the head of sales?",
      "output_schema": {
        "properties": {
          "head_of_sales": {
            "type": "string"
          },
          "sells_to_healthcare": {
            "type": "boolean"
          }
        }
      }
    },
    "name": "ntsb-investigations__research_row"
  }
}

Input Schema

NameRequiredDescriptionDefault
entityYesThe row/company to research. At least one of name/domain required.
sourcesNoWhere to look: "web" (company site only), "catalog" (entity_profile only), "both" (default).
max_costNoCost ceiling in US dollars for this one row. Default 0.02, max 0.50, minimum viable 0.002 (below that the call is refused rather than silently exceeding it).
questionYesThe question to answer about this company, in natural language, e.g. "Does this company sell to healthcare, and who is the head of sales?"
output_schemaYesJSON Schema object naming the fields to extract, e.g. {"properties":{"sells_to_healthcare":{"type":"boolean"},"head_of_sales":{"type":"string"}}}. Up to 20 fields.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.5/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full behavioral burden and does so for the most important trait: it defines the three status values and explains that verification is done by code checking for a verbatim substring rather than being model self-reported. That is genuinely useful context an agent cannot get from structured fields. It falls short of a 5 because the sentence is cut off before finishing the "not_established" explanation, and nothing is said about failure/refusal behavior or latency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose is front-loaded in the first clause, which is good. However, the description is visibly truncated mid-word ("and it"), leaving an incomplete sentence, and the status explanation is run together in one long clause chain. Truncation is a structural defect, not mere brevity.

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?

There is no output schema, so the description must explain returned values; it partially does via the evidence-wrapping and status definitions, but the truncation cuts off the final status meaning. It also does not clarify how the natural-language question relates to the output_schema fields, which matters for a 5-parameter tool with a nested entity object.

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 the schema already documents entity, sources, max_cost, question, and output_schema in detail. The description adds the {value, evidence_url, quote, status} wrapping concept, which is useful but concerns return shape rather than parameter meaning. Baseline 3 applies when the schema does the heavy lifting.

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 uses a specific verb+resource framing: "answer ONE question about ONE company and return a JSON object matching your output_schema." That is far more precise than a restated name. It lacks any explicit differentiation from siblings like deep_research, company_facts, or entity_profile, which is the only thing holding it below a 5.

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?

"Claygent-style per-row research" and the emphasis on "ONE question about ONE company" imply batch/per-row usage, but there is no statement of when to prefer this over deep_research or company_facts, and no exclusions. Usage is inferable but never stated.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.