pg_kill

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

Annotations already indicate destructiveHint=true. The description adds rich behavioral context: explains that cancel is graceful and terminate is forceful, details permission limitations (pg_signal_backend role, superuser requirement for superuser backends), and describes the note field behavior for error feedback.

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 a single paragraph with multiple sentences, but each sentence adds valuable information. It is front-loaded with the main action. Could be slightly more structured (e.g., bullet points), but remains efficient.

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?

Given the complexity (two modes, permissions, error feedback) and absence of output schema, the description covers return value behavior, prerequisites, and permission nuances comprehensively.

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 coverage is 100%. The description adds meaning beyond schema by explaining that mode 'cancel' equals SIGINT and 'terminate' equals SIGTERM, and clarifies the note field for when signaled=false.

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 query or terminates a backend by PID, using specific signals (SIGINT/SIGTERM). It distinguishes from sibling tools by indicating how to find the PID via pg_health or pg_inspect_locks.

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?

The description explains when to use cancel vs terminate, prerequisites (ALLOW_WRITES=1), and permission requirements. It does not explicitly list when not to use or alternatives beyond finding PID, but the context is clear.

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