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

Annotations already mark this destructive, idempotent, and non-open-world; the description pays for itself by adding semantics the annotations cannot convey: cancellation is best-effort ('where possible'), requests already accepted by the platform may still complete, and receipts are retained. It stops short of permission/auth requirements or what happens on a revision mismatch.

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?

Two short sentences, the primary limitation ('where possible') front-loaded, zero filler. Each clause adds a distinct fact an agent needs.

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, so return values need not be described, and the behavioral caveats are well covered for a destructive mutation. However, with four required identifiers at 0% schema coverage and a request_key whose idempotency role is undisclosed, an agent can still misfire on parameter construction.

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% across four required parameters, so the description carries the full burden. It only illuminates one: 'current publication revision' maps to expected_revision as a concurrency guard. workspace_id, publication_id, and especially request_key (an idempotency key) are left entirely unexplained.

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 ('Cancel ... publication') with a scoping qualifier ('future publication', 'where possible') that separates it from publish_social_draft and native.social_cancel_post. It never names a sibling explicitly, so the differentiation is inferred rather than stated.

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?

The phrase 'Cancel future publication' implies the trigger condition (a scheduled-but-not-yet-published item) and 'using the current publication revision' hints at a read-then-cancel flow. No when-not guidance, no prerequisites such as fetching the revision via get_social_publication, and no mention of how it differs from native.social_cancel_post.

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