Skip to main content
Glama

STAS Running Coach for Claude

by run.stas

get_trainings

Use this for completed, finished, recorded, or uploaded activities, including workouts completed today. To load one date D, always set oldest=D and newest=D+1 because newest is exclusive. It returns one bounded, size-safe chronological list of completed workouts plus historical calendar context (NOTE, SICK, INJURED, HOLIDAY). Context is not a workout and does not consume the training limit. Default mode is a rich index for chronology, load, reports, compact summaries, and choosing training_id; use offset to continue beyond the first 50 completed workouts. Set full=true only for analysis-rich comparison across multiple workouts; it adds a bounded compact interval projection. For one selected completed workout, use get_activity_detail for splits and richer detail; kilometre splits are intentionally omitted from get_trainings in every mode. If listDetail.userReportTruncated=true for a workout, its report was shortened only to keep the whole list within the response budget; call get_activity_detail with that training_id for the complete report.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
fullNoOptional analysis-rich list mode for comparing multiple completed workouts in a bounded date window. It adds a size-safe compact interval projection, but is not raw data and is not the detailed view for one workout. Omit it when locating/listing workouts or choosing a training_id; use get_activity_detail after selecting one exact workout.
limitNoMax trainings per page. Server cap is 50.
newestNoEnd boundary date in YYYY-MM-DD, exclusive. Never use the last wanted date here; use the next calendar date. For one day D, set oldest=D and newest=D+1, for example oldest=2026-06-21 and newest=2026-06-22.
offsetNoPagination offset for completed trainings. Use the next offset to continue the same bounded date window; calendar context is returned only on the first page.
oldestNoStart boundary date in YYYY-MM-DD, inclusive.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed1 schema field changed
    • changedInput schema / properties / newest / description
      Previous value: -"End boundary date in YYYY-MM-DD, exclusive. To load one date, set newest to the next calendar date, for example oldest=2026-06-21 and newest=2026-06-22."New value: +"End boundary date in YYYY-MM-DD, exclusive. Never use the last wanted date here; use the next calendar date. For one day D, set oldest=D and newest=D+1, for example oldest=2026-06-21 and newest=2026-06-22."
  2. Changed1 schema field changed
    • addedInput schema / properties / offset
      Added value: +{
+  "description": "Pagination offset for completed trainings. Use the next offset to continue the same bounded date window; calendar context is returned only on the first page.",
+  "maximum": 9007199254740991,
+  "minimum": 0,
+  "type": "integer"
+}
  3. Changed1 schema field changed
    • changedInput schema / properties / full / description
      Previous value: -"Set true when analyzing workouts, reports, intervals, history, or planning context."New value: +"Optional analysis-rich list mode for comparing multiple completed workouts in a bounded date window. It adds a size-safe compact interval projection, but is not raw data and is not the detailed view for one workout. Omit it when locating/listing workouts or choosing a training_id; use get_activity_detail after selecting one exact workout."
  4. Changed4 schema fields changed
    • addedInput schema / properties / full / description
      Added value: +"Set true when analyzing workouts, reports, intervals, history, or planning context."
    • addedInput schema / properties / limit / description
      Added value: +"Max trainings per page. Server cap is 50."
    • addedInput schema / properties / newest / description
      Added value: +"End boundary date in YYYY-MM-DD, exclusive. To load one date, set newest to the next calendar date, for example oldest=2026-06-21 and newest=2026-06-22."
    • addedInput schema / properties / oldest / description
      Added value: +"Start boundary date in YYYY-MM-DD, inclusive."
  5. First observed

TDQS

A4.7/5.0
Behavior5/5

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

With no annotations provided, the description carries the full burden and delivers richly. It discloses the exclusive newest boundary (oldest=D, newest=D+1), that calendar context is not a workout and does not consume the training limit, that kilometre splits are intentionally omitted in every mode, the pagination continuation behavior, and the report-truncation fallback. These are non-obvious behaviors an agent could not infer from the schema.

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 long, but nearly every sentence carries distinct, actionable information: date-boundary semantics, limit-exemption of context, mode selection, sibling routing, and truncation handling. There is no filler or repetition, and the core use case and boundary rule are front-loaded. The length is justified by the tool's complexity, though it approaches the edge of verbosity.

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?

With no output schema and no annotations, the description must carry the return-semantics burden, and it does: it explains the two modes (rich index vs. compact interval projection), the response-budget truncation behavior, pagination, and the context entries that appear alongside workouts. It does not exhaustively enumerate return fields, but for a 5-parameter tool with no output schema, the coverage is strong.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3. The description adds genuine process-level value beyond the schema: the concrete pattern 'oldest=D and newest=D+1' for loading a single day, the rule that offset continues 'the same bounded date window', and the statement that context appears only on the first page. This complements rather than repeats the schema, though the schema already carried most parameter meaning.

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 description opens with a clear verb+resource+scope: 'Use this for completed, finished, recorded, or uploaded activities.' It also distinguishes itself from the sibling get_activity_detail by stating this tool is for listing/comparing while the sibling is for one-workout detail. An agent can select it correctly without opening schemas.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage guidance is explicit and conditional: default mode is for 'chronology, load, reports, compact summaries, and choosing training_id'; full=true is scoped to 'analysis-rich comparison across multiple workouts'; and get_activity_detail is explicitly named for the single-workout case, including the concrete trigger 'if listDetail.userReportTruncated=true'. This is exemplary when-to-use and when-not-to-use guidance.

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

All STAS Running Coach for Claude toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.3/5.0
Disambiguation5/5

Each tool targets a distinct resource and action: plan events vs note events, goals/results vs profile sections, preview vs commit, history vs current sections. The boundaries are clearly defined in descriptions, so an agent can reliably select the right tool for a given task.

Naming Consistency5/5

All tool names follow a predictable verb_noun snake_case pattern with consistent verbs (create, delete, get, preview, commit, read, restore, save). The use of 'get' for data retrieval and 'read' for profile-specific history/sections is internally consistent.

Tool Count4/5

At 20 tools, the set is slightly above the typical 3-15 range, but the complexity of the coaching domain justifies the count. The preview/commit pairs and distinct resource types (goals, profile, plan, notes) each earn their place, though the set could be streamlined by merging some read tools.

Completeness4/5

The tool surface covers the main coaching workflows: reading athlete state, managing training plan and notes, editing goals/results, maintaining profile memory, and saving strategy. Minor gaps exist around explicit creation/deletion of goals and profile sections, which are not clearly supported outside the preview/commit flow.

Resources