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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered; the description adds the non-obvious business consequence that the charged coins are not refunded, which is real value beyond structured fields. It does not describe auth requirements or rate limits, but the refund warning and platform restriction are the high-value disclosures here.

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?

Three short sentences: what it does first, the cost consequence second, the platform restriction last. Every sentence carries actionable information and nothing is redundant.

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?

Output schema exists, so return values need no explanation. The description covers purpose, cost consequence, and eligibility limits, which is nearly everything needed to call it correctly; only the provenance of task_id is left unstated.

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% and the single parameter task_id is documented nowhere, so the description had room to compensate and does not (no guidance on where to source a task_id or its format). Because there is only one required, self-evidently named parameter, this remains minimum-viable rather than broken.

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 (stop/cancel) applied to a specific resource (a submitted task), with a scope qualifier that tasks from web/app are out of bounds. No sibling tool competes for this purpose, so nothing further is needed for differentiation, though it never explicitly contrasts with get_tasks/list_recent_tasks.

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?

"Tasks started on the web or in the app cannot be canceled here" is an explicit when-not-to-use exclusion, which is more than most definitions offer. It stops short of the positive path (how to obtain a valid task_id, e.g. via list_recent_tasks), so there is a small inference gap.

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