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

Far exceeds the annotations (which only mark it as non-read-only, non-idempotent, non-destructive). It discloses that nothing is saved or posted, the ai.generate permission and the exact 403 permission_denied code, the 2-credit cost, the member who is billed, refund-on-failure, the own-provider-key exception, and the no-retry rule when credits are exhausted.

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?

One dense paragraph, front-loaded with the core action and return shape before permissions and billing. Nearly every sentence carries operational value, though the credit/permission detail is lengthy enough that the routing advice gets slightly buried mid-paragraph.

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?

Given an output schema exists, the description need not explain the { caption } payload further, and it volunteers the return shape anyway. Permissions, credit economics, failure handling, and sibling routing together leave nothing an agent needs 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 prompt, platform and workspaceId are already fully documented, so a 3 baseline applies. The description reinforces the platform character-limit behavior and the general-caption fallback, but adds little syntax or semantic nuance beyond what the schema states.

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 ('Write a new social media caption from a prompt') and immediately names the sibling to use for a different need ('To rework a caption you already have, use refine_caption instead'). An agent can distinguish this from refine_caption, generate_image and create_post 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?

Explicit routing: generated output must be passed to create_post, update_post or bulk_schedule_posts because nothing is persisted, and existing captions should go to refine_caption. Also states the pre-post check and the no-retry behavior on exhausted credits. All when/when-not/alternatives are covered.

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