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

Annotations already establish the tool is not read-only, not idempotent, and not destructive. The description adds valuable behavioral detail on top: it returns the updated ProjectDoc plus a list of edits, supports iterative refinement by passing `doc` back, and explicitly does not render an MP4. It stops short of describing persistence or side effects, but the core call behavior is well disclosed.

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?

Three tight sentences without filler: purpose, return value, iteration workflow, and the rendering exclusion. The most important scoping information ('Does NOT render') is front-loaded enough and every sentence earns its place.

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?

There is no output schema, so the description's explicit mention of the return value ('updated ProjectDoc plus the list of edits made') is important and present. It also covers the two common follow-up actions—iterate with `doc` or pass to neuron_studio_render—which is exactly what an agent needs to chain the tool correctly. Given that all parameter details live in the schema, nothing required for a correct call is missing.

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 description coverage is 100%, so the baseline is 3 because the schema already documents all five parameters. The description adds some contextual meaning by tying 'natural-language instruction' to the `instruction` param and mentioning that `doc` is the returned artifact to feed back in, but it does not need to compensate for missing schema information. No parameter semantics are left 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?

The description opens with a specific verb+resource pair ('Build a new video or edit an existing one') and clearly states the input mode is a 'natural-language instruction.' It also sets a firm boundary with 'Does NOT render,' immediately distinguishing this tool from the rendering workflow. This gives an agent a concrete, unambiguous sense of what the tool does.

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 explicitly tells the agent how to continue working with the tool ('Pass the returned `doc` back in to keep iterating') and routes the final output step to a named sibling ('or to neuron_studio_render to produce an MP4'). It also states a clear when-not condition with 'Does NOT render,' which prevents the agent from expecting a rendered file here.

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