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

Annotations already declare readOnly/idempotent/non-destructive, yet the description still adds real value: it clarifies that no calldata is produced and the settle calls submit, that committed markets settle automatically, that GET /claims/receipts is the authoritative source, and how SKIPPED/COMMITTED_SETTLED versus SKIPPED/NOT_CLAIMABLE_YET map to claimed and amountAvailable flags. The one genuinely subtle point — a required amount of zero being a placeholder rather than a credited zero — is called out explicitly.

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 first sentence front-loads the purpose well, but the remainder is a dense block of status-code prose with long compound sentences. 'Nothing is submitted' and 'No transaction is submitted for a committed market' restate the same idea, and the receipts-endpoint aside interrupts the eligibility explanation.

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-shape explanations are optional, yet the description usefully documents the status/flag semantics that the schema alone would not convey. Combined with the explicit no-submission guarantee and committed-market behavior, an agent has enough to call it safely; only the walletAddress default and sibling routing are 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?

With only 50% schema description coverage, the description needed to carry weight here but says nothing about the parameters: walletAddress and its default to the API-key wallet is never mentioned, nor is the 100-market batch cap or the fact that chainId must be a compiled release chain (Base 8453). 'Explicit batch requests' and 'per market' are the only hints at the markets shape.

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: dry-run payout claims and return amounts and eligibility. It is clearly distinguishable from kellian_prepare_claims or kellian_get_claim_status in general terms ('Nothing is submitted'), but it never names a sibling tool, so the differentiation is inferred rather than stated.

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 establishes the domain (onchain markets, committed markets auto-settling) and implies this is a pre-flight eligibility check, but it never says explicitly 'use this before prepare_claims/sweep_claims' or 'do not use this to actually claim'. The routing decision among the several claim-related siblings is left to inference.

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