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

Annotations cover only the safety profile (readOnly, non-destructive, openWorld, non-idempotent); the description adds substantial behavior beyond them: the subscription/Coil Live connector requirement, x402 per-call payment, the PaymentRequired object returned when neither credential is present, and the fact that an unchanged `since` is answered free and never billed. This is exactly the credit-worthy context annotations cannot carry.

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?

Front-loaded with the tool's meaning before the access model, and each sentence carries information. There is mild redundancy around the free-access cases ('free without since' and 'unchanged since is answered free'), which keeps it from being maximally tight.

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 complex, payment-gated diff tool with no output schema, the description covers the diff contents, both access modes, the required credentials, and the no-credential failure shape. An agent has everything needed to decide whether and how to call it, and the return payload is described in prose since no output schema exists.

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% and the single `since` parameter is fully documented there (including the 16-hex-char format and 'omit to receive the current state_hash'). The description largely restates that role, adding only the semantic tie to the previous-call provenance, so baseline 3 is 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 first sentence states a precise verb+resource ('what changed on the board since a state_hash') and enumerates the exact diff categories (READY pool entries/exits, trend-state/light/leadership/hold-band flips, regime/permission-ladder moves). It clearly differentiates a diff-tool from a snapshot tool, but never names the sibling it is distinct from (e.g. get_board_asof or get_day_board), so it falls short of full sibling differentiation.

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?

It gives explicit when-to-use guidance for the two operating modes: pass `since` for a diff, omit it for the current state_hash only, and it discloses the access conditions for each path. It stops short of naming alternative tools to use for other board queries, so an agent knows how to use this tool but not explicitly when to prefer a sibling.

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