create_social_post

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

Annotations already declare a non-destructive, closed-world write, but the description adds genuinely useful behavior beyond them: it never overwrites files, the output name is treated as a stem (so files get suffixed), and photo cutouts default to matched-color plus greyscale exports. It still omits what draft vs final mode changes and whether overwrite protection affects naming collisions.

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?

Five short sentences, front-loaded with what is produced and in which formats, then handoff, naming, and safety constraints. Every sentence carries a distinct fact and none repeats structured data verbatim.

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 tool this complex, coverage is thin: no output schema exists and the schema documents none of the nested properties, while the description covers only formats, naming, safety, and the guidelines prerequisite. It is enough to avoid misuse of the write itself, but an agent cannot know what the many content fields do from this definition.

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 0% against a very large nested content object with roughly forty properties (template enum, scene, portrait, cropPolygon, approvals flags, provenance, etc.). The description only clarifies that outputFileName is a stem and notes the default imageTreatment behavior; the remaining parameters carry no added meaning anywhere.

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 ('Create CP social graphics') and enumerates the four output formats (editable SVG, outlined SVG, PNG, JSON), which is concrete and informative. It does not distinguish this general tool from siblings such as create_cutout_post, create_quote_post, or create_photo_scene_post, even though its template enum overlaps their domains, so an agent must infer the routing itself.

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?

'Call guidelines first' is a real prerequisite, implying get_brand_guidelines should run before this tool. Otherwise there is no when-to-use/when-not guidance: nothing says when to pick this over the template-specific siblings or whether validate_social_post should follow. Usage is only partially implied.

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