CueFrame

Register Critic

register_critic

Idempotent

Register a custom eval into the compose critic panel — the critic contract is { rubric (or rules/evaluator), referenceMediaIds?, floor }. Three tiers: rules (declarative constraints — keep-out regions, required elements, max overlays, brand colors), rubric (a text criterion scored by the judge as an extra column), or evaluator (your HTTPS webhook — CueFrame POSTs the composition+stills+facts, you return { score, critique }). referenceMediaIds (≤6 org media ids) attach YOUR reference frames as the standard — the judge scores candidates for consistency with them, so "indistinguishable from mine" is a machine check. Lane scope: rules + rubric critics run in BOTH lanes (the Director's gates AND standalone score_composition); evaluator webhooks run in the Director lane only. Use phase 'static' (the default) — 'temporal' (final-render evaluation) is accepted but not yet wired, so a temporal critic produces no verdicts today. A low client score drives a refine like a built-in criterion. You see your eval output + our scores, never our rubric. Re-registering the same criticId upserts (list_critics / delete_critic manage the set). Evaluator tier returns a signing secret ONCE.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`body`	Yes	Register a custom compose critic.

Output Schema

TableJSON Schema

Name	Required	Description
`id`	No
`tier`	No
`secret`	No	evaluator tier: Standard-Webhooks signing secret, returned ONCE.
`criticId`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 10, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations cover the write/idempotent/safety profile, but the description adds real behavior: re-registration upserts, low client score drives a refine, the client sees its output+our scores but never our rubric, and the evaluator tier returns a signing secret only ONCE. These are non-obvious operational facts 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.

Conciseness4/5

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

Front-loads the core action and contract before tier details; every clause carries information. It is dense and long, requiring careful reading, but there is little redundancy given the genuine complexity of three tiers.

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?

An output schema exists so return values need no explanation, and the description still covers tier differences, lane scope, phase caveats, upsert behavior, secret delivery, and visibility limits. Nothing an agent needs to call it correctly is missing.

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 already 100%, so baseline is 3, but the description meaningfully enriches semantics: it explains the critic contract shape (rubric/rules/evaluator), what referenceMediaIds actually do ('indistinguishable from mine' as a machine check, ≤6 ids), floor's refine-routing behavior, and what the evaluator webhook receives and returns.

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?

States a specific verb+resource ('Register a custom eval into the compose critic panel') and immediately distinguishes the three tiers it can create. Names sibling managers (list_critics / delete_critic), so an agent can place it precisely in the toolset.

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

Usage Guidelines5/5

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

Explicit when-to-use routing: rules vs rubric vs evaluator, plus lane scope (rules+rubric in both lanes, evaluator Director-lane only). It also warns when NOT to use a feature ('temporal' is accepted but not wired, produces no verdicts today) and points to alternatives for managing the set.

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

All CueFrame tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.