Skip to main content
Glama

Propose durations from recorded runs

calibrate_program
Read-onlyIdempotent

Propose durations for a saved program from its recorded runs: median as the default, P10 to P90 as the range, at least as wide as the author's, with the evidence per step and the effect on total length. Saves nothing; with accept it returns the calibrated program. Needs the user's Rhylthyme account.

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": "calibrate_program"
  }
}

Input Schema

NameRequiredDescriptionDefault
kNoMeasurements a step needs for a proposal (default 5).
sinceNoOnly runs started on or after this date (YYYY-MM-DD or ISO).
tokenNoAccess token from the login tool. Omit when the account is connected.
acceptNoStep ids to accept, or "all": also returns the calibrated program. Nothing is saved either way.
historyNoRun records to use instead of the stored ones.
programNoProgram JSON to calibrate; omit to use program_id's saved JSON.
program_idNoSaved program UUID whose recorded runs are the evidence.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
  2. Changed7 schema fields changed
    • changedInput schema / properties / accept / description
      Previous value: -"Step ids to accept, or \"all\". The result then also carries the calibrated program with `calibratedFrom` beside each written duration. NOTHING IS SAVED either way — pass that program to save_program if the user wants it kept."New value: +"Step ids to accept, or \"all\": also returns the calibrated program. Nothing is saved either way."
    • changedInput schema / properties / history / description
      Previous value: -"Run records to use instead of the ones stored against `program_id` (`runs` schema 0.1.0-alpha)."New value: +"Run records to use instead of the stored ones."
    • changedInput schema / properties / k / description
      Previous value: -"Measurements a step needs before it gets a proposal (default 5). A step under it is reported as skipped with its statistics, not silently dropped."New value: +"Measurements a step needs for a proposal (default 5)."
    • changedInput schema / properties / program / description
      Previous value: -"The program JSON to calibrate. Omit it and `program_id`'s saved JSON is used, so the usual call is just an id."New value: +"Program JSON to calibrate; omit to use program_id's saved JSON."
    • changedInput schema / properties / program_id / description
      Previous value: -"Library program UUID (from list_my_programs). Names the program whose recorded runs are the evidence, and — with no `program` — the JSON to calibrate."New value: +"Saved program UUID whose recorded runs are the evidence."
    • changedInput schema / properties / since / description
      Previous value: -"Only runs started on or after this date (YYYY-MM-DD or ISO), e.g. to calibrate on the last month's cooks only."New value: +"Only runs started on or after this date (YYYY-MM-DD or ISO)."
    • changedInput schema / properties / token / description
      Previous value: -"Your Rhylthyme access token from the login tool"New value: +"Access token from the login tool. Omit when the account is connected."
  3. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already cover the read-only/idempotent/non-destructive profile, and the description reinforces it with "Saves nothing; with `accept` it returns the calibrated program" — useful because the word "accept" could otherwise imply persistence. It also discloses the statistical method and the per-step evidence/effect-on-total output. Minor gap: behavior when runs are insufficient is not stated.

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 and method, followed by two short constraint sentences. Dense but almost every clause carries information; the statistical phrasing ("P10 to P90", "at least as wide as the author's") is compact and earns its place.

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?

For a complex tool with seven parameters, nested objects (history, program), and no output schema, the description qualitatively covers the return (per-step evidence plus effect on total length), the auth requirement, and the non-saving guarantee. It is close to sufficient for correct invocation.

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?

Schema coverage is 100%, so the schema already documents k, since, token, accept, history, program, and program_id in detail. The description restates the accept behavior but adds no new parameter meaning beyond the schema, so the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource ("Propose durations for a saved program from its recorded runs") and even specifies the mechanism (median default, P10-P90 range). This clearly separates it from analysis/review siblings in spirit, though no sibling is named explicitly.

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

Usage Guidelines3/5

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

It states a prerequisite ("Needs the user's Rhylthyme account") and explains the `accept` path, but gives no explicit when-to-use or when-not guidance relative to siblings like analyze_schedule, review_program, or preview_timeline. Usage is only implied.

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.