list_activity

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

readOnlyHint=true already covers the safety profile, and the '[READ]' tag plus the description's note about idle-in-transaction backends holding resources adds genuine context about what gets surfaced. It does not disclose result ordering, row volume, or whether it touches the target server in a costly way.

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?

Front-loads the [READ] marker and a one-line summary, then adds a single relevant caution before the arg list. Every line earns its place; only the args block is mildly redundant with the schema.

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?

With no output schema, the description adequately signals the return shape ('per-state counts', flagged idle-in-transaction backends) and documents all three parameters. Cross-references to sibling diagnostic tools are the only notable omission.

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 schema alone gives only titles and defaults; the description compensates by enumerating valid state values (active, idle, 'idle in transaction'), restating the include_idle default with intent, and explaining that target comes from config and defaults when omitted.

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+resource ('Current sessions (pg_stat_activity) with per-state counts'), naming the underlying catalog view and the shape of the result. It implicitly separates itself from lock/query siblings but never names or contrasts them, so it stops short of full sibling differentiation.

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?

Usage is implied by the 'flags idle-in-transaction backends (open transactions holding resources)' note and the state/include_idle knobs, which tell the agent this is a session-inspection tool. There is no explicit when-to-use versus list_locks or long_running_queries, and no stated prerequisite or exclusion.

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