Create a content item holding a channel-less draft, before any channels are selected. No network-specific validation applies to the draft content. The draft needs text or at least one asset. This API is an early preview and can change without a deprecation period.

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

Annotations already declare the mutation profile (readOnlyHint=false, destructiveHint=true, openWorldHint=true), but the description adds material context beyond them: an explicit-confirmation requirement, an early-preview warning that it may change without deprecation, that no network-specific validation applies, and that provider errors surface as failures even on HTTP 200. Missing only the effect on returned state, but this is notably richer than the annotations alone.

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 first two sentences are a verbatim copy of the tool title, so a meaningful chunk of the text repeats structured data the agent already has, and a stray double period appears where the title was concatenated. The appended sentences are each useful and front-loaded, but the duplication prevents a higher score.

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 an 11-parameter, deeply nested mutation with no output schema, the definition covers identity, stage in the workflow, content precondition, confirmation requirement, and preview instability. It stops short of describing the returned object or the correlationId idempotency behavior (schema-only), but nothing critical for correct invocation 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 91%, so the schema already carries nearly all parameter meaning (including normalized x/y coordinates, video thumbnailOffset, and correlationId idempotency). The description contributes only light hints ('Use upstream fields to bound data' for `fields`, confirmation for `confirm`), so the baseline 3 is appropriate.

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 names a specific verb (create) and resource (content item draft) and adds a genuine scope qualifier: it holds a 'channel-less draft, before any channels are selected', and states the content precondition (text or at least one asset). That scope clause implicitly separates it from create_content_item/create_post, but no sibling is actually named, so differentiation requires inference.

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?

There is usable guidance ('before any channels are selected', 'Requires explicit confirmation', 'Use upstream fields to bound data'), which tells the agent this is a pre-channel stage and needs a confirm flag. However, it never says when to prefer this over create_content_item, create_idea, or create_post, and gives no exclusions or prerequisites for those alternatives.

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