terminate_backend

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

Annotations already declare destructive/not-idempotent/not-readonly, yet the description adds substantial context beyond them: no safe inverse, an audit trail capturing pid+query, a live dry-run preview mode, and the self-pid refusal that applies even during dry_run. This is exactly the behavioral depth annotations cannot express.

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?

Risk tag is front-loaded, followed by impact, preview, and refusal behavior, then an Args block. Every sentence adds information and the param list is warranted given 0% schema coverage. Slightly dense but 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 high-risk mutation with no output schema, the description covers everything an agent needs: irreversibility, audit trail, preview path, refusal constraint, and per-parameter sourcing/defaults. Nothing essential to correct invocation 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 0%, so the description carries the full burden, and it documents all three params: pid (sourced from list_activity), dry_run (preview behavior), and target (from config, omit for default). This compensates well, though pid's expected value range/format is not elaborated.

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 ("Terminate a backend") and maps it to the underlying pg_terminate_backend call, so the effect is unambiguous. The [WRITE][risk=high] tag reinforces the operation class. It does not explicitly differentiate itself from the softer sibling cancel_query, which would have earned a 5.

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?

Gives concrete operational guidance: use dry_run=True to preview, and pid comes from list_activity. The refusal condition (own backend pid, even under dry_run) is spelled out. No explicit when-not/alternative guidance relative to cancel_query, so it stops short of a 5.

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