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

Annotations already declare destructiveHint=true and idempotentHint=true, yet the description adds substantial context beyond them: the exact resulting state (failed, code cancelled), that usage is spent regardless, that a research run stops at Google while a Studio artifact may still finish locally, and that the operation is irreversible.

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?

Four tight sentences, front-loaded with the core action and effect, then the Google/Studio nuance, then the irreversibility warning. Every sentence carries distinct, decision-relevant information with no padding.

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?

No output schema exists, and the description compensates by describing the return (the job, now failed with code cancelled). Combined with the state-change and irreversibility details, an agent has everything needed to call this correctly.

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?

With a single parameter at 100% schema description coverage, the schema already documents jobid, so baseline is 3. The description adds no syntax or format detail for the identifier and merely references 'the job' in the return-value discussion.

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 (cancel a running job) and adds precise scope: it stops tracking and frees the maxJobs slot, leaving the job failed with code cancelled. This clearly distinguishes it from siblings like notebook_get_job (read) and notebook_retry_artifact (re-run).

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 clear when-to-use context (stopping a running job) and an explicit when-not/alternative direction: 'Cannot be resumed: start a new job instead.' It does not name the specific sibling tool for starting a job (e.g. notebook_research), but the routing guidance is unambiguous.

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