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

Annotations cover the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), and the description adds real value beyond them: no render/AI model is invoked, requestId identifies the saved document across retries, and each quote carries its own identity requiring explicit approval. It still doesn't say what the saved scene contains or how retries behave on partial failure.

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

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

The core purpose is front-loaded, but the middle sentences re-enumerate template and look enums already present in the schema, adding bulk without new information. A single dense paragraph makes the useful facts (no paid render, quote identity, approval gating) harder to extract.

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

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

For a 19-parameter mutation tool with an output schema, the description covers the conceptually novel parts (quoting without rendering, asset ownership, approval binding) but leaves over half the inputs undefined. It is workable but not complete for correct invocation.

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

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

Schema coverage is 0% across 19 parameters, so the description carries the load. It explains templates, lookIds, styleIds, asset IDs and requestId semantics, but leaves projectId, family, durationSeconds, aspect, intensity, style, title, trimStartSeconds, artistId, artistName and expectedArtistRevision unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Saves a ready server-rendered Motion scene') plus the exact byproducts (paid-render quote, optional free first-frame preview). This clearly separates it from studio_motion_quote, studio_motion_preview and studio_motion_confirm, whose roles differ.

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

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

The description implies the workflow ('No AI video model or paid render is called', 'rendering requires explicit customer approval bound to that quote') but never names the sibling to call next (studio_motion_confirm) or when to prefer this over studio_motion_quote. Usage is inferable rather than stated.

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