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

Beyond the annotations it discloses latency (halts within a few seconds), the resulting state (status becomes stopped), a cost consequence (points already used are not refunded), and reversibility (deep_resume can continue later). This is exactly the kind of behavioral context annotations cannot convey.

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, both earning their place: the first covers purpose and trigger, the second covers effect, timing, cost, and recovery. The most decision-relevant information (what it does and when) is front-loaded.

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 stop tool with no output schema, the description supplies everything needed: what it acts on, how fast it takes effect, the resulting status, the cost caveat, and how to undo. Nothing material is left for the agent to guess.

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?

The single parameter has full schema coverage, so the baseline applies; however, the schema's own description is only "id" and the prose does not clarify whether this is a run id, thread id, or analysis id. It implies a run identifier contextually but adds no format or sourcing detail.

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?

"Stop a running or queued deep research run" gives a specific verb (stop) plus a precisely scoped resource and state set (running or queued). It is clearly separable from siblings like stop_autopilot or stop_live_session by the resource named, though it never explicitly contrasts with them.

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?

It states the triggering condition (user asks to cancel, or no longer needs the run), which is concrete usage guidance. It also points to deep_resume as the recovery path, but gives no explicit when-not or prerequisite conditions (e.g., what if the run already finished).

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