gtfs-scorecard
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search_agenciesA | Search tracked transit agencies by name, id, ISO country, ISO subdivision or subdivision name, legacy state, or letter grade. Returns portable location, grade, score, expiry, and applicable readiness fields. |
| get_scorecardC | 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. |
| national_statsA | Legacy United States policy view: NTD GTFS readiness nationally and by state, plus the backwards-compatible covered-corpus stats member. Prefer coverage_stats for geography-neutral totals. |
| coverage_statsC | Coverage-wide quality totals and portable country/subdivision rollups over the feeds this scorecard tracks. |
| get_historyA | One feed's dated grade and score history, with every measurement-contract boundary marked. A point marked comparable_with_previous: false was scored under a different rubric, scoring profile, validator, reader archive profile, or measured-category set, and the difference across it is not a change in the feed. Also reports findings that appeared or cleared between the two most recent snapshots, but only when those two are comparable. |
| explain_findingA | The fix recipe for one validator or scorecard notice code, its authoritative rule link, and, when a producing tool is named, that tool's fix path. A code with no written recipe returns the rule link alone and says so; nothing is described beyond what is written. |
| get_rollupB | One program rollup: the cohort's shared fixes, grade distribution, and the members needing attention. Shared fixes describe work many feeds share; they are not a ranking of agencies. |
| get_evidence_packetB | The deterministic vendor remediation packet for one agency's latest scorecard: the producer contract, the work items with their acceptance tests, and the feed identity they were measured against. |
| coverage_forA | Covered-set totals for one ISO country, or one subdivision inside it. A place this scorecard does not track is reported as not covered rather than as zero feeds: absence of coverage is not absence of transit data. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
Three geography/coverage tools overlap significantly: national_stats, coverage_stats, and coverage_for all report aggregate totals by region, and national_stats even instructs users to prefer coverage_stats. get_scorecard vs get_evidence_packet is clearer but still requires reading descriptions to distinguish grade reporting from remediation packets.
All names use uniform lower_snake_case, and most follow a verb_noun pattern (get_history, get_rollup, explain_finding, search_agencies). However, national_stats, coverage_stats, and coverage_for drop the verb and use noun/preposition forms, breaking the pattern for a third of the set.
Nine tools is a reasonable, well-scoped count for a scorecarding domain spanning agency, cohort, and national views. The slight over-provisioning comes from the redundant coverage/national stats trio rather than genuinely distinct capabilities.
The surface covers the full lifecycle: search, agency scorecard, history, finding explanation, remediation packet, cohort rollup, and geographic/national aggregates. No obvious operation is missing, though a bulk export or comparison tool would round it out.