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

With no annotations, the description carries the behavioral burden itself. It discloses the recomputation behavior, the first-divergent-index report, field-based kind detection, and important byte-exactness and float-vs-integer caveats. It could say what happens when all links match, but the output schema likely covers return details.

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 description is front-loaded with the core algorithm and target rows, immediately followed by detection behavior, output, and the most important input nuance. Every sentence earns its place; 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?

Given two parameters, one required, and an output schema available, the description covers purpose, row-kind selection, input format options, and a subtle fidelity caveat. No essential information for invoking the tool correctly is 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?

Schema coverage is only 50%, and the description substantially compensates. It explains the three `kind` values, the detection behavior when omitted, and adds crucial semantics for `entries`: raw text enables byte-exact hashing while parsed arrays lose float formatting distinctions. This goes well beyond the schema.

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 operation ('Walk bernstein chain rows and recompute every link') and enumerates the exact row kinds it applies to, making the tool's scope unambiguous. It is clearly distinct from the sibling verify_receipt despite the similar prefix.

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 explains when the row kind is auto-detected versus when to pass `kind` explicitly, and gives concrete guidance on choosing raw text vs a parsed array. It does not explicitly name alternative tools or exclusion conditions, but the operational context is clear enough for correct use.

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