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

Annotations already declare non-readOnly, openWorld, idempotent and destructive, so the safety profile is covered. The description adds genuinely useful behavior: patch semantics ('omitted fields are preserved'), optimistic concurrency via expectedRevision, and the motion toggle where null reverts to a still – all beyond what annotations say. It does not explain why a draft save carries destructiveHint=true, nor the required bootstrap fields (read_skills, request_key, expected_catalog_version), which remain schema-only.

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?

Four short sentences, front-loaded with the core action and scope, then the edit rule, then the motion edge case. Each sentence carries distinct information; the density of motion detail makes one sentence slightly heavy but nothing is wasted.

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 6-parameter tool with nested objects and a required session/bootstrap payload, the description covers the domain behavior well (motion, revisions, merge semantics) and an output schema exists so return values need not be explained. However, it omits any hint about the mandatory skill-proof and catalog-version prerequisites, which are the most likely failure points for an agent calling this correctly.

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?

With 50% schema coverage, the description meaningfully supplements a few fields: motion's style-vs-preset-vs-null behavior, expectedRevision as an edit guard, and the requirement that IDs be 'observed' rather than arbitrary. Large nested parameters like destinations, promptSharing, connectionIds, publication_proposal_id and work_id get nothing in the description beyond the schema, so it only partly compensates.

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 states a specific verb and resource ('Save a draft') and immediately scopes it ('without publishing'), which is enough to separate it from publish_social_draft and schedule_social_draft without opening either schema. It stops short of naming those siblings explicitly, so it is clear but not maximally disambiguated.

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?

It gives one real usage rule – read styles and presets from the workspace before using motion – and implies the create-vs-edit split via 'use ... expectedRevision for edits'. It never names the alternative tools (publish_social_draft, schedule_social_draft, review_social_draft) or says when not to use it, so the routing is only implied.

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