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

Annotations already establish readOnly/idempotent/non-destructive/closed-world, but the description adds genuinely new behavioral context: inputs are processed transiently and not stored, logged, or retained; execution is deterministic; compute modes can force server or browser delegation; and it exports an AP2 artifact with an execution_hash for chain provenance. These are real traits beyond the annotation set.

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?

It is front-loaded with the name and category, and the data-retention and chaining sentences earn their place. However, it is bloated with boilerplate, an inline tool URL, and a full explanation of the FV-status receipt that adds little to the agent's decision to call the tool.

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 4-parameter, no-required, nested-object tool with no output schema, it covers execution modes, chaining, and output shape (AP2 artifact) adequately. But it never explains the core computation or what policy_parameters must contain, deferring entirely to an external manifest, leaving the semantic gap that matters most.

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%, so the schema already documents compute, parent_hashes, parent_tool_ids, and policy_parameters in detail. The description adds only a pointer that policy_parameters field names live in 'the tool's manifest,' which is marginal value; the compute-mode text largely duplicates the schema. Baseline 3 applies.

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 ('M3P Monthly Cap Calculator') and tags it as an 'OpenChainGraph compute node (payment_policy)', but never explains what an M3P monthly cap is or what the decision function actually computes. It gives a domain label rather than a distinct purpose, which is closer to tautology than a specific verb+resource statement, and offers nothing to distinguish it from the dozens of other compute_* siblings.

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 real usage instruction is 'Use synthetic or anonymised inputs only,' which is a safety caveat rather than when-to-use guidance. It never says when this tool applies versus alternatives, nor what precondition (e.g. a prior policy input or upstream artifact) makes it the right choice.

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