Skip to main content
Glama

adjust_program

Read-only

Adjust a workout and nutrition plan after a check-in, the way a personal trainer would: weight loss stalled, strength stalled, too sore, missed workouts, low motivation, new pain, or block finished (next 6 week block). Changes calories, steps, sets, effort or training days. Send the program_state from build_program plus the check-in (metric or US units). Returns what changed and the updated plan as text and structured JSON.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "program": "<program>",
      "check_in": "<check_in>"
    },
    "name": "adjust_program"
  }
}

Input Schema

NameRequiredDescriptionDefault
programYesThe program_state object returned by build_program (or by the last adjust_program). Send it back unchanged.
check_inYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed18 schema fields changed
    • addedInput schema / properties / check_in / properties / current_weight_lb
      Added value: +{
      +  "description": "Current body weight in pounds, instead of current_weight_kg.",
      +  "maximum": 660,
      +  "minimum": 77,
      +  "type": "number"
      +}
    • addedInput schema / properties / check_in / properties / waist_change_in_last_2_weeks
      Added value: +{
      +  "description": "Waist change in inches, instead of cm. Negative means smaller.",
      +  "maximum": 8,
      +  "minimum": -8,
      +  "type": "number"
      +}
    • addedInput schema / properties / check_in / properties / weight_change_lb_last_2_weeks
      Added value: +{
      +  "description": "Weight change in pounds, instead of kg. Negative means weight lost.",
      +  "maximum": 33,
      +  "minimum": -33,
      +  "type": "number"
      +}
    • removedInput schema / properties / program / properties / profile / properties / days_per_week / anyOf
      Removed value: -[
      -  {
      -    "const": 3,
      -    "type": "number"
      -  },
      -  {
      -    "const": 4,
      -    "type": "number"
      -  },
      -  {
      -    "const": 5,
      -    "type": "number"
      -  },
      -  {
      -    "const": 6,
      -    "type": "number"
      -  }
      -]
    • changedInput schema / properties / program / properties / profile / properties / days_per_week / description
      Previous value: -"Training days per week, 3 to 6."New value: +"Training days per week, 3 to 7 (7 is planned as 6 plus a rest day)."
    • addedInput schema / properties / program / properties / profile / properties / days_per_week / maximum
      Added value: +7
    • addedInput schema / properties / program / properties / profile / properties / days_per_week / minimum
      Added value: +3
    • addedInput schema / properties / program / properties / profile / properties / days_per_week / type
      Added value: +"integer"
    • changedInput schema / properties / program / properties / profile / properties / height_cm / description
      Previous value: -"Height in centimetres. Needed for nutrition targets."New value: +"Height in centimetres. Needed for nutrition targets. Or send height_ft and height_in."
    • addedInput schema / properties / program / properties / profile / properties / height_ft
      Added value: +{
      +  "description": "Height, feet part (US units). Use with height_in.",
      +  "maximum": 7,
      +  "minimum": 3,
      +  "type": "integer"
      +}
    • addedInput schema / properties / program / properties / profile / properties / height_in
      Added value: +{
      +  "description": "Height, inches part (with height_ft), or total height in inches if height_ft is not sent.",
      +  "maximum": 95,
      +  "minimum": 0,
      +  "type": "number"
      +}
    • removedInput schema / properties / program / properties / profile / properties / session_minutes / anyOf
      Removed value: -[
      -  {
      -    "const": 30,
      -    "type": "number"
      -  },
      -  {
      -    "const": 45,
      -    "type": "number"
      -  },
      -  {
      -    "const": 60,
      -    "type": "number"
      -  },
      -  {
      -    "const": 75,
      -    "type": "number"
      -  }
      -]
    • changedInput schema / properties / program / properties / profile / properties / session_minutes / description
      Previous value: -"Session length in minutes. Use 75 for 75 or more."New value: +"Minutes available per session. Any number: the plan uses the nearest fitting length (30, 45, 60 or 75+)."
    • addedInput schema / properties / program / properties / profile / properties / session_minutes / maximum
      Added value: +240
    • addedInput schema / properties / program / properties / profile / properties / session_minutes / minimum
      Added value: +15
    • addedInput schema / properties / program / properties / profile / properties / session_minutes / type
      Added value: +"integer"
    • changedInput schema / properties / program / properties / profile / properties / weight_kg / description
      Previous value: -"Body weight in kilograms. Needed for nutrition targets."New value: +"Body weight in kilograms. Needed for nutrition targets. Or send weight_lb."
    • addedInput schema / properties / program / properties / profile / properties / weight_lb
      Added value: +{
      +  "description": "Body weight in pounds (US units).",
      +  "maximum": 660,
      +  "minimum": 77,
      +  "type": "number"
      +}
  2. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations declare readOnlyHint=true and openWorldHint=false, and the description is consistent with that: it says the tool "Returns what changed and the updated plan", implying a stateless computation rather than persistence. Beyond annotations it discloses the exact levers it can move and the return shape (text plus structured JSON), and it notes the metric-or-US-units input flexibility. It does not describe limits such as whether a check-in with no matching issue produces no change, which is why it is not a 5.

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 with the core action, then the trigger list, the changed variables, the input instruction, and the return shape in a logical order. It is a single dense sentence with colon-delimited lists; every clause carries information, though the length makes it slightly harder to scan than a version split into two or three short sentences.

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?

No output schema, but the description covers the return contract (what changed plus the updated plan as text and JSON) and the input contract (program_state from the prior call, units agnostic). For a two-parameter tool with heavy nesting, the remaining gaps are mostly nested-field semantics already covered, in part, by the schema itself.

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?

With 50% schema description coverage and deeply nested objects, the description only partially compensates: it tells the caller to send program_state unchanged from build_program and to send the check-in in metric or US units. Undocumented areas such as the modifiers fields (block, rir_bump, sets_adjust, at_maintenance, calorie_adjust, daily_steps_add) and several check_in scalars get no extra explanation from the description. Baseline 3 for a case where the schema does most but not all of the work.

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 and resource ("Adjust a workout and nutrition plan after a check-in") and enumerates the concrete triggers it handles (stalled fat loss, stalled strength, soreness, missed sessions, low motivation, new pain, block finished). It also names what it modifies (calories, steps, sets, effort, training days), which is enough to distinguish it from build_program and the other siblings 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?

Clear when-to-use context: after a check-in, with a specific list of reportable situations, plus the timing rule "use block_finished after week 6". It also states the prerequisite input source (program_state from build_program or the last adjust_program). It stops short of an explicit exclusion (e.g. "do not call this before any check-in data exists"), so 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