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

With no annotations, the description carries the full behavioral burden and does well: it discloses price ($0.002 per call), payment rails (x402, USDC on Arc/Base/Solana, XNT on X1), the two-call payment handshake, the 10-minute staleness rule for the sell probe, and the evidence policy ('avoid' only with evidence; every input is shown). It does not state error behavior for an unknown pool/token or what happens if payment terms expire between calls.

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 headline output, then evidence, then the sibling hand-off, then price and payment mechanics – a sensible order with no filler paragraphs. Some phrasing is loose ('returns a score and a call') and the ALL-CAPS opener plus quoted verdict labels are louder than necessary, but no sentence is wasted.

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 paid scoring oracle with no annotations and no output schema, the description is nearly self-sufficient: it covers what is scored, the three verdict states, data freshness, cost, and payment flow. The remaining gap is return-shape detail – beyond `score` and `call`, an agent must infer what 'every input is shown' actually returns (the echoed evidence fields).

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 100%, so pool vs. token and the x402 `payment` payload are already documented in the schema. The description adds modest meaning: 'NO SIZE NEEDED' clarifies that no size argument exists for the buy side, and the payment handshake explains what `payment` should contain across the two calls. That is incremental rather than essential beyond the schema.

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 output: returns 'ONE 0-100 BUY SCORE' plus a verdict ('ok, caution or avoid') for a given Arc pool. It enumerates the exact inputs feeding the score (pool fee, hook permission bits, sell probe freshness, first-buyer behavior, empty pools), and explicitly separates itself from arc_exit_check, which handles sell-side sizing and liquidity-pull testing.

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?

Frames the decision it answers ('Should you buy this Arc pool?') and names the alternative with its selecting condition: 'To test a sell at your own size, or to see whether the liquidity can be pulled, use arc_exit_check.' It also spells out the two-step purchase workflow (call without `payment` for terms, sign, call again with `payment`), which is non-obvious and would otherwise be discovered by failure.

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