Skip to main content
Glama

reference_class_estimate

Read-onlyIdempotent

Generate data-driven task effort estimates by applying historical actual-vs-estimated ratios; use industry averages when no project history exists.

Instructions

Data-driven estimate using reference class forecasting.

Applies historical correction factors based on actual-vs-estimated ratios. When no historical data exists, uses industry averages (1.3-2.2x for software tasks). Prioritize this over algorithmic models when historical data is available.

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": {
      "task_type": "<task_type>"
    },
    "name": "reference_class_estimate"
  }
}

Input Schema

NameRequiredDescriptionDefault
scopeNoRough size of the task: small=tiny fix/tweak, medium=typical task, large=significant effort, xl=epic-scale. When omitted, inferred from complexity (1-2=small, 3=medium, 4=large, 5=xl).
projectNoOptional project/repo identifier this estimate belongs to, for cross-project analytics.
team_idNoOptional team identifier to scope historical data to a specific team.
ai_nativeNoDegree of AI assistance: 0.0 = fully human, 1.0 = fully AI-native, 0.5 = hybrid. Accepts boolean for backward compatibility (true=1.0, false=0.0).
task_typeYesCategory of work being estimated for reference-class lookup.
complexityNoFine-tuning complexity from 1 (trivial) to 5 (extreme). Adjusts within the scope band: low complexity shortens, high complexity lengthens the estimate.
session_idNoOptional session identifier (minted by a calling agent/hook) used to deduplicate repeated estimate calls for the same task within a session.
task_labelNoOptional free-text label identifying the task this estimate is for (e.g. an issue key or short title). Surfaced on get_pending_estimates output for triage.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv0.8.0
    • removedInput schema / additionalProperties
      Removed value: -false
    • removedInput schema / properties / ai_native / default
      Removed value: -1
    • addedInput schema / properties / project
      Added value: +{
      +  "description": "Optional project/repo identifier this estimate belongs to, for cross-project analytics.",
      +  "minLength": 1,
      +  "type": "string"
      +}
    • addedInput schema / properties / session_id
      Added value: +{
      +  "description": "Optional session identifier (minted by a calling agent/hook) used to deduplicate repeated estimate calls for the same task within a session.",
      +  "minLength": 1,
      +  "type": "string"
      +}
    • addedInput schema / properties / task_label
      Added value: +{
      +  "description": "Optional free-text label identifying the task this estimate is for (e.g. an issue key or short title). Surfaced on get_pending_estimates output for triage.",
      +  "minLength": 1,
      +  "type": "string"
      +}
  2. First observedv0.1.0

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely useful behavior beyond that: the correction-factor mechanism, the fallback to industry averages, and the 1.3-2.2x software range. It does not disclose what the call actually returns (a point estimate, a range, a multiplier, reference-class metadata), which matters since there is no output 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?

Four short sentences, each doing work: statement of method, mechanism, fallback, and prioritization rule. The prioritization guidance is placed last rather than front-loaded, but there is no filler or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With eight parameters, no output schema, and a statistical fallback path, the description should say more about what comes back and how the fallback is signaled to the caller. The annotations and full schema coverage reduce the burden, but the return contract remains unspecified, which is the main incompleteness for a tool whose whole value is the number it produces.

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 description coverage is 100%, so all eight parameters including scope, complexity, ai_native and session_id are already documented in the schema. The description adds no parameter-level meaning such as how task_type drives the reference-class lookup or how scope and complexity compose. Baseline 3 is appropriate when the schema carries the load.

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 method (reference class forecasting) and states the mechanism: historical actual-vs-estimated correction factors with an industry-average fallback. It distinguishes itself from the algorithmic-model siblings (cocomo_estimate, pert_estimate) by category rather than by name, which is enough for an agent to route correctly but stops short of an explicit sibling callout.

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?

Gives a clear selection rule: 'Prioritize this over algorithmic models when historical data is available,' plus a documented fallback path when no history exists. It stops short of naming which tool to use instead when history is sparse and the agent doesn't want the industry-average default.

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