Skip to main content
Glama

Nolio

Read training calendar

get_calendar
Read-only

Read a training calendar: your own, a managed athlete's with athlete, or a group's with group.

mode: 'real' (workouts actually done, the default) or 'planned' (the prescription). Both modes render the whole calendar palette over the window, each type its own list, plus has_more per type: planned gives trainings, competitions (with goal_type), cycles (with date_end), notes and quizzes; real gives trainings, competitions (the races actually run, so a realized calendar read without them misses every race), notes (injuries, sicknesses, discomforts and other notes of the realized calendar) and quiz_results (the questionnaires answered, Hooper included, with every answer in items: value is the answer; a choice or a point on a scale reads against choices). An availability note carries duration (the time available) and sports. Every real training and competition carries the athlete's debrief (rpe, feeling, comment, answers to the coach's debrief questions); a coach's comments on a session are in its conversation (read_conversations with event), its laps and curves in get_training. Read it before scheduling anything on a period and surface the conflicts (a race in the window, a cycle already covering it, a duplicate) before proposing. If one type cannot be read the whole call fails (failed names the types): never treat that as an empty calendar. has_more[type]=true means that type's window is incomplete. Read the next page with types=[<type>] and starting_after set to the last returned item's id, keeping the same date_from/date_to/athlete/group/limit: drop group on the next page and you silently switch to your own calendar. Continue until has_more=false before concluding or scheduling. Each mode makes one API request per type (planned five, real four), each subject to the API quota: narrow with types when the question is about one type. types: read only these types of the mode's palette (e.g. ['competitions']). starting_after: next page of a single type, with types naming that one type. athlete: a managed athlete's usr_… handle (from list_athletes) to read their calendar; omit to read your own. An athlete you do not coach is refused (403). group: a grp_… handle (from list_athletes) to read what a group you manage has planned together: the workouts posted on the group itself, not the individual ones of its members. Never pass it with athlete. Planned mode only; a group you do not manage is refused (404). date_from / date_to: 'YYYY-MM-DD' window (omit for the most recent events). limit: max rows per type. Planned defaults to 100 with date_from or date_to, 10 without; real defaults to 10 even with a window. time_in_zones: add the per-zone seconds of every training. Off by default because it is heavy; turn it on only when the question is about intensity distribution. For a whole period, prefer the zones_duration_* chart of get_stats_chart. full_descriptions: planned descriptions are cut to their first 250 characters, flagged description_truncated. Read a planned workout with get_planned_training for its full text, or turn this on over a narrow window; it returns every text of the window. with_description_html: planned mode only, add description_html (the stored description in HTML, never cut) to every event. Read it over the event's date before changing a description that is already set.

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": "get_calendar"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNoreal
groupNo
limitNo
typesNo
athleteNo
date_toNo
date_fromNo
time_in_zonesNo
starting_afterNo
full_descriptionsNo
with_description_htmlNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.9/5.0
Behavior5/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds substantial behavior annotations do not cover: one API request per type (five planned, four real) against a quota, all-or-nothing failure when a type cannot be read (`failed` names the types), `has_more[type]=true` meaning an incomplete window, mandatory pagination details, and `description_truncated` at 250 characters. It even warns that dropping `group` on the next page silently switches to your own calendar, which is exactly the kind of trap annotations cannot express.

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 purpose and mode semantics are front-loaded, and the later paragraphs are organized around parameter names, so it is navigable. It is still long and dense, with some repetition (truncation and get_planned_training are mentioned twice), which keeps it from a 5 for a tool description.

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?

Although an output schema exists, the description still explains the per-type return lists, `goal_type`, `date_end`, `quiz_results.items` semantics, `debrief`, availability `duration`/`sports`, and `has_more`. Combined with the failure and pagination guidance, nothing an agent needs to call this 11-parameter tool correctly is missing.

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

Parameters5/5

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

Schema description coverage is 0%, so the description carries the full burden and does: `types` restricts the mode's palette, `starting_after` needs `types` naming one type, `athlete` takes a usr_… handle from list_athletes, `group` takes a grp_… handle and is planned-mode only, dates are 'YYYY-MM-DD' with omit-for-recent behavior, `limit` has different defaults per mode (100 vs 10 planned, 10 real), and `time_in_zones`, `full_descriptions`, and `with_description_html` each have stated costs and conditions.

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 opening sentence states the exact resource and its three subject scopes (own, a managed athlete's via `athlete`, a group's via `group`), and the `mode` paragraph distinguishes 'real' from 'planned' with concrete contents for each. An agent can tell this apart from `get_planned_training`, `list_planned_trainings`, or `get_stats_chart` without opening a schema.

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?

It gives explicit use conditions and exclusions: read before scheduling on a period and surface conflicts first, prefer `zones_duration_*` in get_stats_chart for whole-period intensity, use get_planned_training for full text, and use read_conversations/get_training for session comments, laps, and curves. It also names the refusal conditions (403 for an uncoached athlete, 404 for an unmanaged group) and forbids combining `group` and `athlete`.

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