Skip to main content
Glama

Starfile

What changed in a record, and when

what_changed
Read-onlyIdempotent

The dated changes in one official record, newest first, edition by edition as the agency published them: for a nursing home (by CCN) its ratings, staffing, citations, penalties and owner organisations; aircraft (N-number) and trials (NCT id) as their history loads. Each change shows the field, before and after, the edition date and the exact source file. Optional since and until dates. Changes about private persons are counted, not shown.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "what_changed"
  }
}

Input Schema

NameRequiredDescriptionDefault
ccnNoNursing home CMS Certification Number (6 characters).
limitNoMax changes (default 25, max 50).
sinceNoOnly changes in editions on or after this date (YYYY-MM-DD).
untilNoOnly changes in editions on or before this date (YYYY-MM-DD).
nct_idNoTrial NCT number.
n_numberNoAircraft tail number.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already cover safety (readOnly, idempotent, non-destructive), yet the description adds real behavioral context: results are ordered newest first, granularity is per-edition as published, each item carries field/before/after/edition date/source file, and — importantly — changes about private persons are counted but redacted from display. That privacy/redaction behavior is a non-obvious trait an agent could not infer from any structured field.

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 and dense: the resource and ordering are stated first, then the per-entity breakdown, then return shape, then the filters and the privacy caveat. Minor deduction for the slightly awkward 'as their history loads' clause, which reads as filler rather than specification.

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?

With no output schema, the description still explains what each returned change contains (field, before, after, edition date, source file) and how private-person records are handled, which is what an agent needs to interpret results. The one small omission is that it never says exactly one of ccn/n_number/nct_id must be supplied, since none are marked required.

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 explains ccn, limit, since, until, nct_id and n_number. The description adds only marginal meaning — that since/until filter by edition date and that results are newest-first, which implies what 'limit' truncates. Baseline 3 is appropriate when the schema carries the parameter burden.

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+resource ('the dated changes in one official record, newest first, edition by edition') and enumerates exactly which record types it addresses (nursing home by CCN, aircraft by N-number, trial by NCT id) plus which fields change (ratings, staffing, citations, penalties, owner organisations). This lets an agent distinguish it from check_nursing_home or company_record without opening any schema.

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?

Usage is clear from the entity-type routing — a CCN for nursing homes, an N-number for aircraft, an NCT id for trials — and the 'since/until' framing makes the temporal-history use case obvious. It stops short of naming alternatives or stating when NOT to use it (e.g., use check_nursing_home for a current snapshot), so it is a 4 rather than a 5.

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.

Resources