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

Annotations only supply readOnlyHint and openWorldHint, so the description carries the real behavioral burden and does so well: it discloses a per-call price, the exact failure mode (unpaid calls return x402 PaymentRequirements), and the recovery protocol (pay with an x402-MCP client via _meta "x402/payment" and retry). That is meaningful operational context an agent could not infer. It stops short of describing rate limits, latency, or the shape of the returned table.

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?

The pricing information is stated twice — once as 'Costs $0.05 USDC (x402)' and again in the bracketed block 'Paid: $0.05 USDC per call via x402 (Base or Solana)'. The opening sentence is well front-loaded with the useful content, but the bracketed duplication wastes space.

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 tool with no output schema, the description does the important work of naming the metrics returned and explaining payment/retry, but it leaves the nested 'prices' input unexplained and says nothing about error handling, partial results, or what happens when a ticker is unknown. An agent has enough to attempt the call, but not enough to use it well.

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 0% with two parameters, and the description only touches 'tickers' — restating the max of 12 that the schema already enforces via maxItems. The 'prices' parameter is a nested object of numbers and is left completely unexplained, so an agent cannot tell whether it is optional input prices, a currency map, or an override for the comps calculation.

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 resource (a trading comps table) and enumerates the exact columns returned (market cap, EV, EV/Revenue, EV/EBITDA, P/E, P/FCF, margins, peer medians) with the 12-ticker cap. This is clearly distinguishable from siblings like get_lbo or spread_bank_statement, though it never explicitly contrasts itself with get_financials or get_gpu_comps, which are the closest alternatives.

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 by the metric list and the paid-call mechanics, but there is no statement of when to choose this over get_financials or get_gpu_comps, nor any precondition or exclusion. The retry instruction covers how to call it, not when to use it.

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