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

Annotations cover the safety profile (readOnly, idempotent, non-destructive), and the description goes further by disclosing transient processing with no storage/logging/retention, deterministic execution, the gpu:true browser-delegation rule, and the exported AP2 artifact carrying an execution_hash. That is genuine behavioral context beyond the annotations, though return format and failure modes remain unstated.

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 first two sentences are near-verbatim repetition ("M3P Monthly Cap Calculator: OpenChainGraph compute node (payment_policy). Deterministic OpenChainGraph compute node."), and the closing FV-status/URL block is marketing boilerplate rather than invocation-relevant content. Front-loading is present but the payload is buried until the last clause.

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 no-output-schema computation tool, the description should say what is computed and returned; instead it points to an external "manifest" for field names and offers no domain semantics for the decision function. Runtime plumbing is covered, but the actual tool semantics an agent needs to call it correctly are absent.

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 thoroughly; the description's compute-mode explanation largely duplicates the compute enum description. It adds no field-name guidance for policy_parameters and instead defers to an external manifest, which is not helpful at call time.

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 title and name identify the resource ("M3P Monthly Cap") and the verb (calculate/compute), but the description never states what the cap is, what inputs drive it, or what rule it applies. Almost all of the text is generic OpenChainGraph runtime plumbing that could be pasted onto any of the hundreds of sibling compute_* tools, so it does not differentiate this tool from compute_mla_mapr or compute_scra_rate_cap.

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 no statement of when to use this tool versus the sibling compute_* tools, nor any domain context (which regulation/policy the monthly cap belongs to). The only guidance offered — "Use synthetic or anonymised inputs only" — is an input constraint, not a selection criterion.

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