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

Annotations only declare readOnlyHint=true, so the description earns credit for adding real context beyond them: it discloses that invocation is paid via x402 with USDC on Base (a precondition the agent must surface to the user) and that the operation is stateless with nothing persisted (a data-handling guarantee). It stops short of describing error modes, minimum sample requirements, or return shape.

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?

Three short sentences with no filler, and the cost/payment notice is correctly front-loaded so an agent sees the precondition before anything else. The statelessness note lands at the end where it belongs. Nothing is wasted, though the middle sentence packs two distinct operations (fit and apply) without separating them.

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?

With no output schema, the description should at least imply the return value; 'recalibrate the given probabilities' hints at a same-length array of adjusted probabilities but never confirms it. The most consequential gap for a fitting tool is the absence of any minimum-examples or degenerate-input guidance, which is exactly what causes failed calls. Payment and statelessness are well covered, so it is adequate but not complete.

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%, so the description must carry the load. It does explain both parameters semantically — 'examples' as labelled {p,y} outcome pairs and 'probs' as the probabilities to recalibrate — which is more than the bare schema offers. But it omits the practical semantics that matter for isotonic fitting: minimum number of examples, whether probs must lie in [0,1], and whether output order/length matches input.

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: fit isotonic calibration on labelled {p,y} outcomes and recalibrate the supplied probabilities. An agent knows exactly what computation happens. However, it never distinguishes itself from the sibling court_recalibrate, which by name covers very similar ground — the key differentiator (user-supplied labels vs. server-side model) is only implied by 'YOUR labelled outcomes'.

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 implied rather than stated: 'YOUR labelled outcomes' signals the precondition that the caller must already hold labelled pairs, and 'the given probabilities' implies they are passed in. There is no explicit when-to-use/when-not, and the near-identical sibling court_recalibrate is never mentioned as the alternative for callers who lack labels.

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