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

No annotations are supplied, so the description carries the full burden and does so: it discloses cost (free, anonymous 10/min per IP, no daily cap), latency (<100ms), auth (none), data scope (attested tier only), and a genuine caveat that counts are a LOWER BOUND because evicted entries or restarted isolates lose history. That lower-bound warning is the kind of trait an agent could not infer from schema or name.

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 with the purpose sentence, then cleanly sectioned into When/Returns/Cost/Latency so an agent can skim. Slightly longer than necessary — the latency and cost sections are useful but the returns field list is dense — and the hard line-wrapping breaks sentences mid-clause, which is a minor readability cost.

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 and no annotations, the description correctly compensates by enumerating the response shape (`agents[]` fields, `count`, `limit`) and noting the honesty fields. The gap is that the honesty fields (`counts_are`, `counts_note`, `scope`, `would_have_paid_usd`, `verify`) are named but never explained, leaving an agent to guess what they contain.

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 100% and the single `limit` parameter is fully documented there (default 50, max 100, clamping behavior). The description adds no syntax or format detail about `limit` beyond echoing it in the returns list, so baseline 3 applies — the schema is doing all the parameter work.

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 and scope: every agent public key reported by an attested tollbooth site, with summed request count, newest first. It immediately delimits itself against the sibling `agent_record` (single-key read) and against verdict-producing tools ('facts, not verdicts: no score, no tier, no IP'), so an agent can pick it out of a ~90-tool list.

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?

Explicit 'Use this tool when' bullets cover both the discovery case ('which agents the commons has a record for') and the routing case ('picking a key to read with `agent_record`'), which names the alternative and the condition that selects it. The scope line 'attested tier only' implicitly excludes unattested data, so the main boundary is stated.

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