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

With no annotations, the description carries the full burden and does: it states the probe is unauthenticated and read-only with no payment signed, discloses the free-tier row cap, and notes the total counts so the caller can gauge how partial the slice is. It also explains that every response embeds an unlock/paid_upgrade block, which is exactly the kind of side effect annotations could not convey.

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 text is dense but well-structured and front-loaded: purpose first, then args, then returns, then source/paid-upgrade. A few clauses are repetitive (the free-tier cap is implied twice) and it is longer than strictly needed, but almost 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?

With no output schema, the description enumerates the return fields (agent_id, chain, endpoint_url, http_402_ok, network, asset, price_usd, payTo_present, sibling_agent_ids, probed_at) plus the totals, which is exactly what the agent needs to interpret results. It even names the provenance probe, though field_test_url is referenced but omitted from the row list — a trivial gap.

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 and it does: `chain` is documented as one of "base" or "ethereum" with omit-for-both semantics (the schema declares no enum), and `limit` is bounded to 1..10 with the free-tier cap and default of 10. This adds essential meaning the bare schema lacks.

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?

Names a concrete resource (a directory of ERC-8004 agents that passed an HTTP 402 x402 challenge) with the qualifying condition, so the agent knows exactly what surface it enumerates. The explicit 'OBSERVATION ONLY — not a score, ranking, or endorsement' line draws a boundary against ranking-style siblings like get_leaderboards. Verb+resource+scope is unambiguous.

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?

Gives clear calling context: all args optional, `{}` returns the top 10 across both chains, and the free tier caps at 10 rows. It also explains the paid counterpart and when enrichment is warranted, but it never routes the agent to a specific sibling by name. Strong context without explicit alternative selection.

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