Skip to main content
Glama

estimate_sanity

Read-onlyIdempotent

Deterministic classifier for story/task hour estimates against benchmarks: flags each estimate in_range, borderline, over, under, or unbenchmarked. Supply either an explicit {min, max} range per type (benchmarks) or a list of historical actual hours per type (historical) that this endpoint derives a mean/stdev variance band from - explicit ranges win when both are given for the same type. No benchmark numbers are built in; a type with neither input is reported unbenchmarked, never guessed at. POST one estimate or a batch (max 200). Deterministic, no LLM.

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": "estimate_sanity"
  }
}

Input Schema

NameRequiredDescriptionDefault
flag_zNoDefault 2.0. Stdevs from the historical mean beyond which a result is "over"/"under" instead of "borderline". Must be >= borderline_z.
estimateNoOne estimated item.
estimatesNoAlternative: batch of up to 200 items.
benchmarksNoOptional. Per type: {min?, max?}. Wins over historical for the same type.
historicalNoOptional. Per type: array of past actual hours (max 500 each), used to derive mean/stdev when no explicit benchmark exists for that type. Needs at least 2 values to produce a band.
borderline_zNoDefault 1.0. Stdevs from the historical mean before a result is "borderline" instead of "in_range".

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changed
    • changedInput schema / properties / estimate / description
      Previous value: -"One item: {id?, type, hours}. type and hours are required."New value: +"One estimated item."
    • addedInput schema / properties / estimate / properties
      Added value: +{
      +  "hours": {
      +    "description": "Estimated hours.",
      +    "minimum": 0,
      +    "type": "number"
      +  },
      +  "id": {
      +    "description": "Optional id, echoed back and listed when flagged.",
      +    "type": [
      +      "string",
      +      "number"
      +    ]
      +  },
      +  "type": {
      +    "description": "Work type your benchmarks/historical are keyed by (e.g. \"feature\"), not a task description. Matched case-insensitively.",
      +    "type": "string"
      +  }
      +}
    • addedInput schema / properties / estimate / required
      Added value: +[
      +  "type",
      +  "hours"
      +]
    • addedInput schema / properties / estimates / items / description
      Added value: +"One estimated item."
    • addedInput schema / properties / estimates / items / properties
      Added value: +{
      +  "hours": {
      +    "description": "Estimated hours.",
      +    "minimum": 0,
      +    "type": "number"
      +  },
      +  "id": {
      +    "description": "Optional id, echoed back and listed when flagged.",
      +    "type": [
      +      "string",
      +      "number"
      +    ]
      +  },
      +  "type": {
      +    "description": "Work type your benchmarks/historical are keyed by (e.g. \"feature\"), not a task description. Matched case-insensitively.",
      +    "type": "string"
      +  }
      +}
    • addedInput schema / properties / estimates / items / required
      Added value: +[
      +  "type",
      +  "hours"
      +]
    • addedInput schema / properties / estimates / maxItems
      Added value: +200
  2. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already cover read-only/idempotent/non-destructive, yet the description adds substantial behavior: deterministic with no LLM, no built-in benchmark numbers, batch cap of 200, historical needing at least 2 values, and the precedence of explicit ranges over derived bands. These are exactly the constraints an agent needs to predict outcomes.

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-loads the purpose and the output vocabulary, then moves to input rules and limits, with zero filler sentences. The dense em-dash-separated clauses make it slightly harder to scan than a cleanly bulleted structure would be.

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?

With no output schema, the description carries the return-value burden and does name all five flag values plus the fact that ids are echoed back and listed when flagged. It does not sketch the overall response envelope (counts, per-item structure), which is the remaining gap for a batch-capable tool.

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

Parameters4/5

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

Schema coverage is 100%, so baseline is 3; the description still adds meaning by explaining that historical values are converted into a mean/stdev variance band and that benchmarks override historical per type. It does not restate flag_z/borderline_z, which the schema already documents well, so it stops short of a 5.

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?

Opens with a specific verb+resource: 'Deterministic classifier for story/task hour estimates against benchmarks', and enumerates the exact output labels (in_range, borderline, over, under, unbenchmarked). No sibling tool in the list does estimate classification, and the description makes that scope 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?

Gives concrete input-selection rules: supply benchmarks or historical, explicit ranges win when both exist for a type, and a type with neither is reported unbenchmarked rather than guessed. It does not name alternative tools or when-not-to-use conditions, but no sibling overlaps, so the practical guidance is strong.

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.