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

Annotations only cover read-only/idempotent/destructive/open-world flags, while the description adds substantial behavioral context: a concrete cost (0.01 USDC on Solana), the settlement endpoint, the payTo address, the 402-challenge retry flow, the required PAYMENT-SIGNATURE/X-PAYMENT header, and the explicit statement that the server does not custody funds. This is exactly the kind of operational detail annotations cannot convey.

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?

Purpose is front-loaded in the first sentence, with payment details following in a logical order. The text is dense but each clause carries actionable information (cost, endpoint, payTo, retry, custody), though the parenthetical '(not by this MCP host)' and restatement of the header flow add slight redundancy.

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 single-parameter, no-output-schema tool, the description covers the critical unknowns: cost, payment protocol, retry semantics, and fund custody. It does not explain failure modes beyond 402 or whether payment is mandatory for every call, which are minor residual gaps.

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% for the single 'text' parameter (with min/max length bounds), so the schema already carries the parameter semantics. The description adds no format, encoding, or content guidance beyond what the schema states, making the baseline 3 appropriate.

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 opening sentence gives a specific verb, resource, and even the output shape ('summarize text into 1-3 concise sentences'). It is easily distinguished from siblings like sol_token_brief or tts, which address unrelated resources. It loses a point only because the rest of the description is dominated by payment mechanics rather than the summarization task itself.

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 description gives procedural invocation guidance (call the tool, handle HTTP 402, pay, retry with the payment header), but says nothing about when to choose this tool over alternatives or what input it is/isn't suited for. Usage is implied by the obvious 'summarize text' framing rather than stated.

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