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

No annotations exist, so the description carries the full burden. It does disclose the real consequence — the in-flight turn and all queued messages are discarded — which is the most important behavioral fact for a stop operation. It says nothing about reversibility, authorization scope, or what remains of the task record afterward.

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 sentence with no padding, and the core action is front-loaded after a short qualification. The client-gating clause is the weakest part and slightly obscures the action, but 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?

For a two-required-parameter mutation tool with no annotations and no output schema, the description leaves the critical unknown unanswered: how to identify the agent and task. It also omits whether the stop is idempotent or what is returned, gaps the structured fields cannot fill.

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?

Both required parameters ('agent', 'task') are bare strings with 0% schema description coverage, and the description does not clarify whether they take IDs, slugs, or names. The phrase 'an agent's task' only restates the parameter names rather than adding semantics.

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 ('stop an agent's task') and even scopes the effect ('the turn running now and the messages waiting in it'), which separates it from task_wait, task_status and task_reply. It never names a sibling explicitly, so differentiation is inferential 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?

'For clients outside Caddie acting for the user' is a gating condition rather than guidance: an agent cannot tell whether it is such a client, or what to use instead if it is not. The 'as Stop on the Agents page does' analogy helps orient the reader but gives no when/when-not rule against task_wait or agent_reply.

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