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

With no annotations, the description carries the full behavioral burden and does not meet it. It doesn't say whether the asset survives cancellation, whether partial output is retained, what happens if no generation is running, or whether permissions are required — all critical for a mutating cancellation call.

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?

A single front-loaded sentence with no filler and the operation up front. It is efficient but borders on under-specified rather than maximally concise.

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 mutation tool with no annotations and no output schema, one sentence is insufficient. An agent still lacks the precondition for a valid call, the failure mode, and what state the asset is in afterward.

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 50%: notification_message carries a rich schema description covering format and constraints, while asset_id is undocumented but self-evident. The description adds nothing about either parameter, but the schema does most of the work, so the baseline 3 applies.

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?

Specific verb ('cancel') plus specific resource ('in-progress generation for a project asset') — notably not the asset itself, which separates it from delete_project_asset. It never names the sibling it could be confused with, so the differentiation has to be inferred from the wording alone.

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 'in-progress generation' implies a precondition (only meaningful while a job is running) but never states it as guidance, and gives no alternative for a finished or failed asset. No mention of delete_project_asset or cancel_publishing_history as the adjacent routes.

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