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

Adds substantial behavior beyond the annotations: no credit cost, existing guides reused so repeats are safe, rendering happens without an open browser, missing guides start while failures are retried, and concurrency is described (one or two clips at a time, a few in parallel for larger batches with the rest queued). This reframes the destructiveHint=true/openWorldHint=true annotations as a safe, idempotent operation and tells the agent what to expect on latency.

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?

Front-loads the target and scope, then layers cost, safety, and concurrency in a logical order with no filler sentences. It runs long, and the concurrency sentence ('one or two clips start at once, and for more clips a few render at a time while the rest wait their turn') is wordier than needed, but every sentence carries usable information.

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 mutation tool with an output schema and six parameters, the definition covers scope, cost, idempotency, failure retry, throughput, and when to defer to sibling tools instead. An agent can decide whether to call it, what it will affect, and whether it must poll afterward without further information.

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?

The undocumented parameters are exactly the ones the description explains: keyframe_grid ('also renders the 3×3 grid used when a video model can't follow a motion guide') and the clip_ids/scene_id precedence rule. The remaining opaque fields (work_id, request_key, expected_catalog_version) are session plumbing left to the schema, which keeps this below a 5 given only 50% schema description coverage.

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?

Names the specific action (ensure/render 3D guides) and resource (image guide matching each clip's Image tab format, motion guide, optional 3×3 keyframe grid) and scopes it to a Film's 3D clips. It also distinguishes itself from the sibling read/wait tools by name, so an agent can separate it from native.inspect_film_three_d and native.wait_for_film_three_d_guides without opening any schema.

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?

Gives explicit when-not-to-use guidance: 'Image and video generation wait for the guides on their own; use wait_for_film_three_d_guides or inspect_film_three_d only when you need the guides yourself.' It also spells out the default target set (every 3D clip of the Film, or of scene_id, when clip_ids is omitted), which is the main selection ambiguity.

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