cancel_query

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

With no annotations, the description fully discloses high risk, audit logging, no undo, and self-prevention. It transparently states the operation is destructive and 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?

The description is front-loaded with risk tags, and each sentence provides critical information. No redundancy; compact yet thorough.

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 high-risk mutation tool with no output schema, it covers purpose, parameters, and side effects. It lacks return value details but that is acceptable for a cancellation action.

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 schema has 0% description coverage, but the description details each parameter: pid from list_activity, dry_run for preview, target from config. It adds necessary context beyond the schema's titles.

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?

The description clearly states the tool cancels a running query via pg_cancel_backend. It distinguishes itself from siblings like terminate_backend and reset_query_stats by focusing on the query itself and noting the no-inverse property.

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 explains when to use (cancel a query) and when not (refuses its own backend pid). It advises using dry_run for preview. However, it does not explicitly contrast with alternatives like terminate_backend.

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