Delete a content item: the item itself and any posts created from it. Deletion is all-or-nothing. Every post must be deletable on its own, or nothing is deleted and every blocked post is reported at once. A post can only be deleted while it is a draft, awaiting approval, scheduled, or failed, so an item cannot be deleted while any of its posts is publishing or already published. An item still holding a channel-less draft has no posts, so nothing blocks it. An error can also be reported when a post could not be fully processed after the deletion already took effect; re-fetch before retrying. 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?

Substantially exceeds the annotations (destructiveHint=true, idempotentHint=false) by disclosing all-or-nothing deletion semantics, blocked states, the special channel-less draft case, the post-deletion error case with a re-fetch-before-retry instruction, and the preview/no-deprecation-period caveat. This is exactly the behavioral context an agent needs for an irreversible mutation.

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-loaded with the core action and scope, and each subsequent sentence carries real semantic weight about blocking conditions and retry behavior. It loses a point only because the title is reproduced verbatim as the description body, creating duplication.

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 destructive, non-idempotent mutation with no output schema, the description covers failure modes, blocking rules, and post-error recovery guidance. It stops short of stating what a successful response contains or how partial provider errors surface, though the 'provider errors are failures even with HTTP 200' note partially bridges that.

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 the baseline is 3. The description only marginally adds meaning — 'Use upstream fields to bound data' loosely connects to the fields parameter and 'Requires explicit confirmation' echoes the confirm parameter's own schema text — while account, payload, and payload_file get no narrative elaboration.

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 ('Delete a content item') and explicitly extends scope to 'any posts created from it', distinguishing it from the sibling delete_post. An agent can tell what is removed without opening the 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?

Gives concrete preconditions: a post must be draft, awaiting approval, scheduled, or failed, so an item with a publishing/published post cannot be deleted, and items holding only a channel-less draft are unblocked. It does not name the alternative tool (delete_post) for the case where only one post should be removed, leaving the routing inference to the agent.

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