Skip to main content
Glama
iftahs
by iftahs

measure_subframes

measure_subframes

Measures subframe quality metrics—FWHM, eccentricity, SNR, PSF weight, star count, noise—and stores results for selection.

Instructions

SubframeSelector measurement of (debayered) frames: FWHM, eccentricity, SNR weight, PSF signal weight, star count, median, noise per frame, plus spread statistics. Stored in the session for select_subframes. Async.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
waitNo
filesYes
camera_gainNoe-/ADU; default from rig
pixel_scaleNoarcsec/px; default from rig

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already indicate this is a mutating operation (readOnlyHint=false) and not destructive. The description adds valuable behavioral context: it is asynchronous, stores results in the session, and requires debayered frames. It does not detail side effects on existing session data or failure behavior, but the async disclosure and session-storage note go beyond the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences with no filler. The core action and metrics are front-loaded, the session-storage side effect is stated, and the async behavior is a single word at the end. Every sentence 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 4-parameter tool with no output schema, the description covers the main inputs' purpose, the async behavior, and the downstream consumer. It does not specify the return value or how to retrieve results, but the session-storage note and sibling select_subframes imply the workflow. The missing wait parameter semantics is a minor gap given the async disclosure.

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 50%: files and wait lack descriptions, while camera_gain and pixel_scale have descriptions. The description does not explain the files parameter's format or the wait parameter's semantics, so the agent must infer them. However, the description's mention of 'default from rig' for camera_gain and pixel_scale adds context beyond the schema, and the overall purpose clarifies what files refers to.

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 states a specific verb ('measure') and resource ('(debayered) frames'), and enumerates the exact metrics computed (FWHM, eccentricity, SNR weight, etc.). It also names the downstream consumer (select_subframes), which distinguishes it from sibling tools like measure_stars and image_statistics.

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?

The description implies the tool is a prerequisite for select_subframes and notes it operates on debayered frames, giving clear context for when to use it. It does not explicitly state when not to use it or name alternatives, but the sibling list and the explicit 'Stored in the session for select_subframes' provide adequate routing guidance.

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