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

With readOnlyHint/openWorldHint already covering the safety profile, the description adds genuinely non-obvious behavior: $0.003 per successful call via x402 paid in the call's _meta across named chains, failed calls free, the twenty-candidate cap at one finalized block, pair-creation ordering rather than first-liquidity time, and background scan/re-scan cadence with stale-verdict caveats. The V4 restriction tied to min_wrapped is also disclosed. It stops short of describing return shape or what a 'collector candidate' record contains.

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?

Every sentence carries information, but it is one dense run-on paragraph of semicolon-chained clauses and parentheticals, and high-value facts (payment cost, x402 mechanics) are buried at the end rather than front-loaded. Purpose leads correctly, but the structure makes scanning harder than it needs to be.

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 no-output-schema tool with payment and staleness semantics, the description covers cost, billing mechanics, scan cadence, ordering, and candidate cap — the things an agent cannot get from structured fields. Gaps remain around the `arc` chain value and what a candidate entry actually returns, but the critical decision inputs are present.

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 high (80%), and the description still adds real meaning: min_wrapped is explained as a wrapped-coin reserve threshold whose zero value unlocks V4 pools, and verdict is framed as an optional stored verdict (with the caveat that stored verdicts may be old). It leaves the `arc` chain value in the schema enum entirely unexplained and says nothing about how `limit` interacts with the 20-candidate cap beyond restating it.

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 verb and resource: filter the latest collector candidates on one chain down to currently funded markets, with concrete criteria (V2/V3 pools against the wrapped coin above the minimum reserve, V4 pools with active liquidity). It never names a sibling (feed, scan, scan-lite, verdict) or explains why one would pick this over them, so it is clear but undifferentiated.

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?

Usage is implied through filtering criteria (funded-only, optional stored verdict, max 20 candidates, single finalized block), which lets an agent infer the suited scenario. There is no explicit when-not-to-use statement and no routing to alternatives such as `feed` or `scan`, so the agent must guess at boundaries.

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