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

Goes well beyond the readOnly/idempotent annotations: it discloses transient, non-retained input handling, the server-vs-browser delegation split for gpu:false vs gpu:true nodes, and that an AP2 artifact with execution_hash is exported for chain provenance. The FV-status receipt note adds verifiability context, though it is tangential to invocation.

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 front-loaded content is infrastructure boilerplate rather than the tool's purpose, and the closing FV-status paragraph is a long, low-value sentence about offline receipt verification. Substantial text is spent on generic compute-node policy that applies to every sibling in this family.

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 tool whose core input is a free-form nested policy_parameters object with no properties enumerated and no output schema, the description never explains what fields the decision function expects or what the result looks like. An agent can construct compute and parent hashes but cannot meaningfully populate the decision inputs.

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%, so compute, parent_hashes, and parent_tool_ids are already documented; the description only adds the chaining/provenance framing for parent hashes. Critically, policy_parameters — the actual decision inputs — are left opaque ('See the tool's manifest for field names'), which the description does nothing to remedy.

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 essentially restates the name and title ('EBA IM-Model Validation Tracker: OpenChainGraph compute node (compliance_mandate)') without saying what is actually computed — no verb describing the validation-tracking decision function. It never distinguishes this from close siblings such as assess_model_validation_status, run_model_test_battery, or compare_model_outcome_analysis.

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 only guidance offered is about execution mode (compute:'auto' vs 'browser') and data hygiene ('Use synthetic or anonymised inputs only'). There is no statement of when an agent should pick this tool over the many model-risk siblings, and no prerequisites or exclusions.

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