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

With no annotations at all, the description carries the full burden and does real work: it discloses the monetary cost and payment rail (USDC on Solana), that the output is signed, and the NO-FUNDS PROPERTY that every probe payload is cryptographically invalid and cannot move funds - a critical safety disclosure for a tool that sends POST garbage at third-party endpoints. It omits failure-mode behavior (payment failure, repeat-charge semantics) and rate limits.

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?

Two sentences, front-loaded with the price and what the payment buys, then the safety property last as a highlight. The parenthetical probe list is dense but each item is load-bearing; nothing is redundant.

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 an unannotated, paid, outbound-probing tool with no output schema, the description is unusually complete: it specifies cost, payment rail, report contents, and the no-funds guarantee. Gaps remain around error/payment-failure behavior and whether repeated calls re-charge, which matter for an agent deciding to invoke.

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 baseline would be 3, but the description adds meaning the schema does not: pricing is per endpoint, one call covers exactly one named endpoint, and the probe set is fixed rather than selectable. That clarifies that the single url parameter has no configurability.

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 description names a specific verb (run the 7-probe set) and resource (rail-coverage and reject-shape probe report), and even enumerates the probe set (baseline GET, HEAD, POST-unpaid, direct-rail garbage, etc.) plus the report contents (grade per rail, method matrix, exposure findings). What it never does is differentiate itself from the sibling rail_probe_precheck and rail_probe_criteria, so an agent must infer the routing.

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 is only implied: the '$0.02 USDC per endpoint' framing tells the agent this is a paid, single-endpoint action, which is contextually useful. There is no explicit when-to-use, no statement that a free precheck or criteria tool should be consulted first, and no mention of an alternative among the many siblings.

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