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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, so the bar is lower — yet the description adds real value beyond them: transient input processing with no storage/logging/retention, deterministic execution, browser-delegation URL returned for gpu:true or compute:'browser', and an exported AP2 artifact carrying execution_hash for provenance. That is substantive behavioral disclosure for a compute node.

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 text is front-loaded reasonably (name/label first) but bloated: the trailing FV-status snapshot clause with a 64-character hash and the 'not a subscription; verifies offline regardless' aside consume space without helping an agent decide or invoke. Several sentences describe the OpenChainGraph platform rather than this tool, diluting the signal.

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?

An output schema exists, so return values need not be explained, and the description covers chaining, compute modes and privacy. But for a compliance compute node with a nested policy_parameters object it never states which policy fields are expected, and it never describes what the amortization actually produces or its governing assumptions — the agent must consult an external manifest.

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 description coverage is 100% and the four parameters are already fully documented in the schema, so the baseline is 3. The description echoes the compute-mode semantics that the schema already defines and says nothing about the contents of policy_parameters beyond 'See the tool's manifest', adding no meaning 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 restates the title ('ASC 340-40 Commission Amortization') and labels the tool a 'compute node (compliance_mandate)', but never says in plain terms what it computes — e.g. that it builds a capitalized commission amortization schedule from reconciled commission data. It does distinguish itself contextually by naming its upstream artifact (art-266-reconcile-commission-statement), which hints at its role in a chain, but the core verb+resource statement is largely tautological.

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?

There is meaningful operational guidance: compute mode semantics (auto/server/browser), the 'synthetic or anonymised inputs only' restriction, and the note that it consumes upstream artifact art-266. However, nothing says when to use this tool versus the many sibling amortization/build-schedule tools, nor any prerequisites for ordering it in a chain.

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