Skip to main content
Glama

sim_calibrate

Destructive

Calibrate a model against YOUR event log — the reading that meets reality. Upload CSV (case_id, activity, timestamp; the shape sim_dataset emits, activities = transition ids), and rates are learned from the observed timings: sources from inter-arrival times, services from the gap before their completions, all per hour. Instant-pickup transitions (declared rate >= 100) keep their declared rate — their observed gap is the queue wait, and learning it would destroy the calibration discipline. A transition declaring a delay (a fixed-duration timer, not a rate) is fit differently and returned in learnedDelays instead of learnedRates: the MEDIAN observed gap, in hours, written onto the transition itself since a delay has no solver-map slot — a gapCV in rateEvidence far from 0 means the log looks exponential, not fixed, and the calibration says so in a caveat rather than trusting the median anyway. Returns a NEW content-addressed model (learned rates in the solver map, learned delays on the transitions, declared values otherwise untouched, lineage recorded) plus a conformance report: fittingPercent (full replays) is the headline, worst traces named with the activities that could not fire. tokenFitness is a second, harsher reading of the same replay (raw tokens present vs. required at every step, not full-trace success) that under-reads any net with a resource pool — read fittingPercent, not tokenFitness, unless you specifically want the raw-token number. Every learned rate or delay has an entry in rateEvidence: n (gaps it rests on), gapCV (sample std dev over mean of those gaps; ~1 for exponential timings, near 0 for a true timer) and insufficient when n < 2 — n=0 yields nothing, n=1 a value with no spread. Learned values on a structure that cannot replay the traces would be numerology — read fittingPercent before trusting them.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idYesmodel id to calibrate
logYesthe event log, as CSV text

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior5/5

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

The description extensively discloses behavior beyond annotations: it returns a new content-addressed model rather than mutating the original, explains how instant-pickup transitions and delay transitions are handled, and warns that learned values on non-replayable structure are unreliable. No contradiction with annotations (destructiveHint: true, readOnlyHint: false) — it clarifies the actual effect.

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 each sentence carries weight, covering input format, learning logic, output interpretation, and caveats. It's front-loaded with the core purpose and then systematically explains nuances. Slightly dense, but no wasted words given the complexity.

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?

For a tool with this complexity (rates, delays, conformance reports, evidence fields), the description is remarkably complete. It explains output semantics (fittingPercent vs tokenFitness, rateEvidence fields like n, gapCV, insufficient) and provides actionable guidance on trust. Nothing critical is missing for an agent to call it correctly.

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 coverage is 100% for both parameters, but the description adds substantial meaning: it specifies the exact CSV format (case_id, activity, timestamp) and clarifies that activities are transition ids. This goes beyond the schema's terse descriptions and is essential for correct invocation.

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 'Calibrate a model against YOUR event log' — a specific verb (calibrate) and resource (model). It clearly differentiates from sibling tools like sim_evaluate or sim_conformance by focusing on learning rates from observed timings. The purpose is unambiguous.

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?

It provides context on when to use it (when you have an event log to fit against) and gives interpretation guidance (read fittingPercent over tokenFitness). However, it doesn't explicitly contrast with alternative tools or state when not to use it, leaving some inference to the agent.

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