states_table

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

With no annotations, the description carries the full behavioral burden, and it does well. It clearly signals read-only via the '[READ]' prefix, discloses pagination/truncation semantics ('truncated' is true when the state table holds more entries than returned), and documents the return envelope structure with field names and types. This transparency about truncation is genuinely useful for an agent handling large tables.

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 '[READ]' signal immediately, then a one-line purpose. Parameter docs and return format are kept brief. No wasted sentences or redundant prose. Slightly verbose in the envelope detail but each element 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?

For a read-only query tool with only 2 optional params and no output schema, the description covers the essential contract: what it reads, the two parameters, and the return envelope including the critical truncation flag. No annotations exist to lean on, so the description does the heavy lifting and covers the practical gaps (pagination behavior, default target). This is complete for the tool's complexity level.

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?

The schema has 0% description coverage, and both 'top' (how many state entries to return, default 100) and 'target' (firewall target name from config; omit for the default) are explained in the description. This adds real value beyond the bare schema. However, the guidance is serviceable but not deeply detailed—e.g., it doesn't clarify the valid range or behavior of 'top' at extremes, though defaults and nullability are covered.

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 this reads 'Active pf state-table entries (connections currently tracked)', identifying the verb (read) and the resource (pf state-table entries). It distinguishes itself from siblings like kill_states (destructive), rule_states (rule-specific), and firewall_log (logs), though it doesn't explicitly name alternatives. Clear and specific enough to stand apart from the majority of sibling read tools.

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 this is a read-only query tool for current connection tracking, and there's an explicit note about returning truncated results when the table exceeds the limit. However, it doesn't explicitly state when to use this vs alternatives like top_talkers or firewall_log, nor does it note conditions like 'use this for real-time connection visibility'. No explicit when-not-to-use guidance or named alternatives.

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