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

The description adds significant behavioral context beyond the annotations: 'Inputs are processed transiently to compute the response and are not stored, logged, or retained', 'Exports an AP2 artifact with execution_hash for chain provenance', and the compute delegation logic (browser delegation URL for gpu:true or browser mode). Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, and the description aligns with these, adding details on data retention and artifact generation. No contradiction.

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 dense and somewhat repetitive, opening with 'Royalty Split Validator: OpenChainGraph compute node (compliance_mandate). Deterministic OpenChainGraph compute node.' This repeats the compute node identifier. It packs in many details (compute modes, transient processing, artifact export, FV-status URL) that are relevant but could be better organized. The front-loading of purpose is helpful, but the repeated phrase and technical clutter reduce conciseness.

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?

The description covers compute modes, data retention, artifact export, and FV-status, which are relevant given the tool's complexity. However, it does not describe the validation logic or the expected response format (no output schema exists). While it mentions 'Exports an AP2 artifact with execution_hash', it doesn't clarify what the actual validation result looks like (e.g., boolean, report). For a tool that validates royalty splits, this is a notable omission.

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?

The input schema provides 100% coverage, describing all four parameters (compute, parent_hashes, parent_tool_ids, policy_parameters) with their meanings. The description adds minimal parameter-related info: it explains the compute modes and the transient nature of inputs, but does not enrich the semantics of parent_hashes, parent_tool_ids, or policy_parameters beyond the schema. Since schema coverage is high, the baseline is 3, and the description does not add significant value here.

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 opens with 'Royalty Split Validator' and identifies it as an 'OpenChainGraph compute node (compliance_mandate)', clearly indicating its role as a validator for royalty splits. It also adds 'Deterministic' which suggests a fixed computation. However, it does not explicitly state what aspects of a royalty split are validated (e.g., sum, proportions), nor does it differentiate from calculation tools like calculate_erc2981_royalty beyond the validator title. The purpose is clear enough but lacks specificity on validation criteria.

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 provides usage guidance on input data ('Use synthetic or anonymised inputs only') and compute mode selection (auto/server/browser behavior), but it does not state when to choose this tool over alternatives, such as royalty calculation tools or other validators. There are no explicit exclusions or alternative tool references. The guidance is operational (how to run) rather than contextual (when to use).

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