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

Annotations already declare readOnly/idempotent/non-destructive, so the description focuses on what those hints cannot convey: the simulation is quote-based rather than an actual trade, which contract attributes are read, what failure patterns are surfaced (honeypot route, tax, thin liquidity), plus rate limits (10 free/day), pricing ($0.003/call), payment mechanism (params._meta['x402/payment'], HTTP, X-API-Key), and the serving host. Auth and cost disclosure is exactly the extra context annotations cannot provide.

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 primary action and what it detects, then the commercial details. The final sentence packs pricing, two payment paths, and a host name, which is dense but each element is operationally actionable; nothing is pure filler.

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 three-parameter, single-call check with an output schema already present, the description covers purpose, method, detection targets, cost, and authentication. An agent has everything needed to decide whether to call it and how it will be billed, with return-value detail delegated to the output schema.

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% and each parameter (usd size, chain list, token address) is fully documented in the schema with examples and bounds. The description adds no parameter-level meaning such as what test size is sensible or how chain selection affects quote availability, so it sits at the baseline.

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 resource (ERC-20 token) and a concrete two-part mechanism: a simulated USDC→token→USDC round trip using aggregator quotes, plus contract reads (owner, proxy, paused, supply). This is distinguishable from sibling checks like solana_mint_check or mcp_token_measure, which are different chains or metrics.

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?

The opening clause 'Before buying an ERC-20' gives a clear decision point for invocation, and 'flags no-sell-route... high round-trip loss' explains what justifies acting on the result. It stops short of naming an alternative tool or stating when not to use it (e.g., for already-held tokens or non-ERC-20 assets).

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