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

Goes far beyond the annotations: nothing is persisted or posted, requires ai.generate, names the roles that hold it (Admin/Editor/Contributor, not Viewer) with the exact 403 permission_denied code, and discloses the 2-credit cost per call, refund-on-failure, the bring-your-own-key exemption, and the no-credit failure path with 'do not retry automatically'.

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 what it does and what it returns, then layers permissions, credits and failure handling in a logical order with no filler sentences. It is a dense block, but nearly every clause carries actionable 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?

An output schema exists, yet the description still names the return shape and, more importantly, covers the cost, auth, quota-exhaustion and no-side-effect semantics an agent needs before calling a generation endpoint. Nothing material is left to inference.

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 coverage is 100%, so prompt, platform and workspaceId are already fully documented in the schema — the platform character-limit line is essentially restated. The description adds no semantics beyond the schema, so the baseline 3 applies.

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') plus the exact return shape ({ caption }, text only). It also separates itself from the two nearest siblings: the post-creation tools it feeds and refine_caption for reworking existing text.

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?

Explicitly says the output must be passed to create_post, update_post or bulk_schedule_posts yourself, and names refine_caption as the alternative for reworking an existing caption. The instruction to check returned text against the platform character limit before posting is a concrete when-to-use caveat.

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