top_talkers

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

readOnlyHint=true already covers the safety profile, so the description earns credit for adding behavior beyond it: the exact response envelope and the meaning of 'truncated' versus 'total'. It stops short of noting units, sort order guarantees, or any rate/performance caveats.

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-loaded one-line purpose, then compact Args and Returns blocks. The envelope explanation is the only multi-line section and it directly prevents misreading the truncation flag, so every sentence earns its place.

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?

There is no output schema, so the description supplies the return shape, and both parameters are documented despite 0% schema coverage. For a two-parameter read-only aggregation tool, nothing needed to call it correctly 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 coverage is 0%, so the description must carry the load and it does: 'top' is explained as the number of talkers returned (default 20) and 'target' as a firewall target name from config with explicit omit-for-default semantics, which the schema's bare string/null typing does not convey.

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 resource ('busiest source hosts') plus the aggregation source and metric ('aggregated from the state table by bytes'), which cleanly separates it from siblings like states_table (raw rows) and firewall_log. An agent can identify the tool's output purpose 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?

The '[READ]' prefix and 'aggregated from the state table' hint at read-only traffic-volume analysis, and the target arg notes 'omit for the default'. But there is no explicit when-to-use/when-not guidance or routing to states_table, firewall_log, or blocked_traffic_rca for related questions; selection must be inferred.

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