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

Annotations already declare non-read-only, non-destructive, idempotent semantics, so the description isn't carrying the safety burden alone. It still adds real context beyond them: cancel is a publication-level operation and does not remove content already live on the network, which no annotation expresses.

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 sentences, front-loaded with the action and its granularity, then a clarifying caveat. Every clause adds information an agent needs to call this correctly.

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 one-parameter, non-destructive, idempotent tool with no output schema, the definition covers scope, ID sourcing, and the live-post caveat. It does not say what happens when the target post is already canceled or already live (error vs. no-op), which is the last remaining gap.

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 0%, so the description must compensate for the single undocumented parameter, and it does: it explains what publication_id identifies (one network of one video) and which endpoints surface it. It omits the ID format or an example, so it is not fully self-sufficient.

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 ('Cancels one scheduled post') and pins the unit of granularity to 'one network of one video', which an agent could not infer from the name alone. It stops short of distinguishing itself from near-siblings like retry_publication or move_publication.

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?

Tells the agent where to obtain the required identifier ('publication_id is in get_video or get_calendar'), which is concrete routing guidance. It also excludes a case ('posts already live are not deleted'), but never names the alternative tool to use for live posts or for rescheduling.

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