Vixdeo — Tu Productor IA

Judge the script

judge_script

The house critic's judgement of a script version — the same independent critic the writing pipeline uses, reading the deterministic quality report alongside. Returns scores 0-100 (global, fidelity to the material, channel voice, rhythm), per-scene notes with severity, and the quality report. Each note says where it comes from (source): critic is the model's reading, audit is a contradiction checked against the research material without a model. factualAudit is the deterministic half: per scene, which facts it cites (citations), whether that backing was cited by the script, inferred from its text, or is text the author dictated in the request (dictated_in_the_request: a disclosure or a closing line — it is not a factual claim and is left out of factualScenes), and what happened to each on-screen figure the material does not carry (onScreenClaims[].outcome): notAsserted = it is not shown (stripped from the text, or its magnitude withheld from the chart), drawnWithoutFigure = plotted without its number, stillAsserted = left on screen; placeholders counts, also without a model, text that names with a letter or an order number what the source does not name («Repository A», «Server 1») or leaves a template marker («N/A», «TODO»), per scene and surface (narration, screen, caption); inputs.script says which document was judged (vbp = the version's blueprint, with its citations). scope states what the critic judges (judges: script) and what it does not see (seesCharts, seesPeriods): the charts and each figure's period are covered by the fidelityReport of the project status. Judgement only: it does not rewrite. The verdict is kept on the version as the critic wrote it; the critic judges in one language for every reader, and the notes returned are presented in the reader's language (notesLanguage says which, and whether they were translated). Defaults to the head version. Requires write. Spends one critic call (small, seconds), plus a short translation of its notes when the reader's language is not the critic's.

Input Schema

Name	Required	Description	Default
`project_id`	Yes
`version_id`	No	Optional: a specific version; default the project's head.

Schema Changelog

Changes observed during successful MCP inspections.

First observedSep 27, 2026

TDQS

A4.2/5.0

Behavior5/5

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

Annotations only declare the mutation profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false). The description adds what the annotations cannot: the `write` permission requirement, the cost ('one critic call (small, seconds), plus a short translation'), and the persistent side effect ('The verdict is kept on the version as the critic wrote it'), which explains why this is not a read-only call.

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

Conciseness3/5

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

Purpose is front-loaded, which is good, but the body is a single dense paragraph saturated with backticked field names and nested parentheses that is hard to scan. Some of that bulk is defensible given there is no output schema, but the structure is poor.

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?

With no output schema, the description carries the full return-value burden and does so thoroughly: score dimensions, per-scene notes with severity, `source` values, `factualAudit` semantics, `onScreenClaims[].outcome`, `placeholders`, and `inputs.script`. It also discloses permissions, cost, persistence, and judging scope, so an agent has everything needed to invoke it correctly.

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

Parameters2/5

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

Schema coverage is only 50%: `project_id` is undocumented in both schema and description, and the only parameter detail given ('Defaults to the head version') merely repeats the schema's own `version_id` description. With half the parameters undocumented, the description does not compensate for the coverage gap.

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 names a specific verb and resource ('the house critic's judgement of a script version') and immediately bounds the scope: 'Judgement only: it does not rewrite,' which separates it from rewrite_script. It also pins down what is out of scope (charts, periods), so an agent can distinguish it from siblings without opening a schema.

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 gives clear operating context: the same critic the writing pipeline uses, defaults to the head version, requires `write`, and spends one critic call plus a translation. It stops short of an explicit when-to-use/when-not routing against siblings like generate_script or rewrite_script, though 'it does not rewrite' implies the boundary.

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

All Vixdeo — Tu Productor IA 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.

Resources

Need Help?