Fetch an agency's GTFS scorecard by agency_id to see its overall grade, category scores, top fixes, findings with effort estimates, and NTD readiness.
An agency's latest scorecard: overall grade, category scores and plain-language summaries, every finding with its fix and effort, top fixes, and NTD GTFS readiness.
| Name | Required | Description | Default |
|---|---|---|---|
| agency_id | Yes | Agency slug, e.g. 'unitrans' |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. 'Latest' hints at freshness, but nothing states that this is a read-only operation, whether results are cached, what happens for an unknown agency_id, or any auth requirement. Enumerating the payload partially compensates, but the core behavioral profile is absent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single efficient sentence with no filler; content is front-loaded. It is a content list rather than a purpose statement, so it is concise but not optimally structured for tool selection.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with no output schema, listing the returned sections (grades, findings, fixes, NTD GTFS readiness) is genuinely useful. However, the description leaves out what the tool actually does, when to invoke it instead of siblings, and any read-only/freshness behavior — substantial gaps given no annotations.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There is a single parameter (agency_id) and the schema documents it at 100% coverage, including an example slug, so the baseline is 3. The description adds no meaning about the parameter at all — it never references the agency argument.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description names a specific resource (an agency's latest scorecard) but supplies no verb — it is a noun-phrase inventory of contents rather than a statement of what the tool does. An agent can infer retrieval, and 'scorecard' distinguishes it somewhat from siblings like get_history and get_rollup, but it never explicitly says 'fetch/retrieve a scorecard for an agency'.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no guidance on when to use this tool versus the eight siblings (get_history, get_rollup, get_evidence_packet, explain_finding, etc.). No prerequisites, no exclusions, no indication of how it relates to rollup/history views.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.