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

Annotations only cover readOnlyHint and openWorldHint, and the description adds substantial behavioral context beyond them: per-call pricing and settlement rail, the refund/no-charge rule, and the precise semantics of async=true (the core source is checked before the job is queued and charged). It also discloses that a model generates the score/red flags and that a PDF is produced.

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 deliverable and dense with useful specifics rather than filler, so most sentences earn their place. It is a single long multi-clause sentence followed by two dense ones, which makes the billing and async rules easy to skim past.

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?

There is no output schema, so the description carries the return-shape burden and does so: it enumerates report contents, states the score/red-flags/metrics/PDF artifacts, and covers cost, refunds and async delivery. For a 4-param, 1-required read-only tool that is complete.

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%, so the baseline is 3; the description earns more by explaining that async delays the job and changes when charging occurs, which the schema's terse 'Return a job id now and the report later' does not convey. It also notes pdf defaults to true. webhook_url is left entirely to 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?

Names a specific artifact (DeFi protocol due-diligence report) and enumerates the contents it returns: TVL windows and peak, TVL by chain, fees/revenue annualised, DEX volume, audits, incidents, oracles, forks, governance-token risk, news. This is clearly distinguishable from raw-data siblings such as defi_tvl, defi_fees and defi_dexs, which do not synthesize a scored report.

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 context is implied (due-diligence on a protocol) and the description is unusually explicit about cost ($3 USDC via x402) and the no-charge condition when too few sources answer, which helps the agent decide whether to spend. However, it never states when to pick this over cheaper sibling endpoints (defi_tvl, defi_fees, defi_dexs) or when a report is overkill versus a point lookup.

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