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

Annotations already establish readOnly, idempotent, openWorld, so safety is covered. The description adds genuinely new behavior: the return contract (verdict of ok/caution/avoid with reasons, plus an assessment of ok/unverified/high_slippage_risk/high_sandwich_risk/blocked) and the cost model (0.005 USDC per call, included in subscriptions). Latency and rate limits are not mentioned, but this is well beyond annotation coverage.

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?

Two dense sentences: one front-loading the checks, one covering verdicts and pricing. Every clause carries information and there is no filler, though the checklist style reads as a run-on rather than tightly structured prose.

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 high-complexity multi-signal preflight with no output schema, the description does the necessary work by disclosing the verdict enum and the underlying assessment codes so the agent knows how to read the result. Only ancillary details (latency, whether the sandwich share is historical vs simulated, rate limits) are missing.

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?

With 75% schema description coverage on four parameters, the schema already carries most of the parameter meaning (mint, quote default SOL, amount units by side). The description adds no parameter-level detail at all — the lone gap, the 'side' enum, is left undocumented in both places.

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 names a specific verb-scope ('Before a Solana swap') and enumerates exactly what is checked: price impact, sandwich share, Token-2022 transfer fees, hooks, permanent delegate, mint/freeze authority. That enumeration is far more concrete than the sibling names pool_health or token_deep_check. It stops short of naming a sibling to differentiate from, so it is clear but not fully disambiguated.

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?

'Before a Solana swap' gives an explicit temporal trigger for when to call it, which is stronger than implied usage. It never says when NOT to use it or which sibling (pool_health, token_deep_check) covers a narrower case, so an agent still has to guess at boundaries with overlapping tools.

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