top_talkers

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

With no annotations provided, the description carries the full behavioral disclosure burden. It explicitly declares [READ] semantics at the start, describes the output envelope in detail including the 'truncated' flag which discloses the pagination/limitation behavior, and explains what 'truncated: true' means. This is strong transparency for a read-only aggregation tool without annotations.

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 compact and front-loaded with the core purpose (first sentence), followed by a clearly separated Args section and a Returns section. The envelope specification is efficient — it lists field names rather than describing each verbosely. Minor inefficiency: the '1' in the example envelope and explanation of 'truncated' is slightly redundant given the envelope already shows the field names.

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 read-only aggregation tool with a well-specified output envelope, the description covers the key elements: what is returned, the truncation behavior, and parameter semantics. The output envelope doubles as a de facto output schema since no formal output schema exists. The main gap is not explaining what the 'target' parameter refers to more concretely or what happens when no target is specified versus specifying the default.

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 must compensate. It does explain 'top' (how many talkers to return, default 20) and 'target' (firewall target name from config, omit for default). However, the description's parameter info largely restates what the schema already encodes (default values), adding only marginal context like 'from config' for target. It covers both params but adds little beyond the schema defaults.

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 verb+resource: 'Busiest source hosts, aggregated from the state table by bytes.' The [READ] prefix signals this is a read operation and distinguishes it from write tools like undo_apply, reconfigure, toggle_rule, and kill_states. It's specific about the aggregation metric (bytes) and source (state table), clearly separating it from sibling tools like states_table and rule_stats.

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 implies usage context by naming the data source ('state table') and how it aggregates (by bytes), which suggests when it's appropriate to call. However, it does not name alternative tools or give explicit when-to-use/when-not-to-use guidance compared to siblings like rule_stats or states_table, which could serve similar reporting functions.

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