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

Goes well beyond the readOnly/openWorld/idempotent annotations: discloses the x402 paid flow, the 402 challenge on the first call, that the 402 and any >=400 error are not charged, that failed post-payment calls settle nothing, that down feeds surface in 'sources', that 404 means no matching headline, and that feed text is data not instructions. That is unusually rich behavioral context.

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?

Price and paid-tool warning are front-loaded and each paragraph carries information. It loses a point for redundancy: the 'not charged' guarantee is stated three separate times across the description, which could be consolidated.

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?

An output schema exists, so return-format explanation is not owed, yet the description still sketches the result shape (link, publisher, time, summary) and covers the failure modes an agent will actually hit (402, 404, partial sources). Nothing needed to invoke it correctly is 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?

Schema coverage is 100%, so the baseline is 3, but the description adds meaning: 'every word must appear' for query, the 1-168 hour window framing for sinceHours, and the full first-call/second-call dance for payment (402 carries howToPay.payloadTemplate; sent as PAYMENT-SIGNATURE header, never body data). Only the limit default 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?

States a specific verb+resource (latest crypto headlines) plus the exact scope: nine named newsrooms merged, de-duplicated, newest first, with link/publisher/time/summary. No sibling tool in the list covers news, so the agent can select it without cross-checking schemas.

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?

Explains the operating context clearly: filter by keywords and a 1-168 hour window, omit query for everything. It also routes the agent to the practical path ('the fiatdock-mcp npm package pays automatically') versus the 402 challenge. It does not name an alternative sibling for news, but none exists to disambiguate against.

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