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

Annotations already declare read-only, idempotent, non-destructive, closed-world, so the bar is lower; the description still adds real value by stating inputs are processed transiently, nothing is logged or retained, and that synthetic/anonymised inputs are required, plus the AP2 execution_hash export behavior.

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 stated purpose is buried behind repeated boilerplate ('OpenChainGraph compute node (compliance_mandate). Deterministic OpenChainGraph compute node.'), a long hash URL, and an FV-status disclaimer, and the one-line summary is cut off mid-sentence. Much of the text does not earn its place.

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?

There is no output schema, but the description enumerates the returned fields (risk_score, risk_tier, enisa_control_coverage_pct, remediation_checklist, etc.) and points to describe_tool for the full schema, which is adequate for a deterministic scorer. The undocumented nested policy_parameters keys are the remaining gap.

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 the schema already documents compute, parent_hashes, parent_tool_ids and policy_parameters. The description's compute-mode sentence restates the schema, and it adds nothing about the nested policy_parameters keys (all undocumented in both schema and description), so baseline 3 is right.

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 verb+resource ('Score ICT vendor due-diligence posture against NIS2 Art. 21(2)(d)') and the artifacts it consumes/feeds, so it is distinguishable from the sibling score_nis2_incident_significance. The purpose statement is however truncated ('against NIS2 Art.') and buried after a wall of runtime boilerplate.

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 compute-mode selection ('auto' vs 'server' vs 'browser', GPU delegation) and the upstream/downstream chain (consumes art-144, feeds art-146), which is implied usage context. But there is no explicit 'use this instead of X' guidance against the many other NIS2 siblings such as check_nis2_art21_measures or run_dora_readiness_diagnostic.

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