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

Annotations already declare destructiveHint=true, so the safety profile is covered, but the description goes further: it names the possible backend responses ('Query cancelled', 'Cancellation requested' for durable runs, 'No active query found') and prescribes the post-call workflow of polling until run_status reports 'cancelled'. That is meaningful behavioral context beyond the structured fields.

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?

The destructive warning is front-loaded in caps, followed by usage constraint, then return values, then follow-up steps. Every sentence carries operational value; no filler.

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 destructive action with full annotation and schema coverage, the description supplies everything an agent needs: the trigger condition, the possible outcomes, and the required next step. Nothing material is missing.

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 100% for the single session_key parameter, so the schema carries the semantic load. The description adds no format, source, or retrieval guidance for session_key beyond what the schema states, which is the baseline case.

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 up front ('stops an AI edit that is currently running') and scopes it to a single running operation. An agent can distinguish it from siblings like dreamagent_get_chat_status or dreamagent_chat without opening the schema.

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?

Explicit when-to-use ('Use ONLY when the user explicitly asks to stop/cancel the active edit') and explicit when-not-to-say ('do NOT claim the requested change was completed'). It also names the follow-up tools (dreamagent_get_chat_status / dreamagent_get_edit_progress) and the target state to poll for.

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