Create Post

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

Adds substantial behavior beyond the annotations: publishing is asynchronous per platform and 'the response is not the outcome' — the agent must read list_post_results; a future scheduledAt sets status SCHEDULED while omitting it publishes immediately; saveAsDraft defers validation to publish_draft; and mediaUrls from outside upload_media fails with 'Media file(s) not found in storage'. No contradiction with readOnlyHint=false or destructiveHint=false — creating a post is a non-destructive write.

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 description is long (~200 words) but information-dense, and every sentence earns its place given 24 parameters, 9 platforms, per-platform configs, and async behavior. The core action and modes are front-loaded, and sibling routing is at the end. A minor deduction only for slight near-duplication of TikTok/Pinterest requirements that the schema's own param descriptions already enforce.

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 of this complexity, nothing material is missing: prerequisites, platform-specific config routing, async semantics, the response-is-not-the-outcome caveat, the mediaUrls failure mode, and alternatives are all covered. The output schema and 100% parameter coverage carry the remaining details, so the description does not need to enumerate every config field.

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 the baseline is 3, but the description adds critical semantics the schema cannot express: the cross-parameter mapping from each platform enum to its corresponding connection-id array ('linkedinConnectionIds, pageIds for Facebook, and so on, one account per platform'), the mediaUrls provenance requirement (must come from upload_media), and the behavioral state transitions for scheduledAt and saveAsDraft. This is exactly the kind of relational guidance the flat schema lacks.

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+resource ('Create one post') with clear scope ('one or more platforms') and names the three execution modes: publish now, schedule, or draft. It also distinguishes itself from siblings by explicitly naming bulk_schedule_posts, update_post, and publish_draft, so an agent can tell them apart without opening their schemas.

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?

Gives an explicit prerequisite ('Call list_accounts first') and explains why: each platform needs its connection-id array filled from it. Names alternatives with selection conditions: bulk_schedule_posts for many posts on the same accounts, update_post/publish_draft for an existing post. Also gives platform-specific requirements (TikTok needs tiktokConfigs with privacyLevel, Pinterest needs pinterestConfigs with boardId).

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