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

This is a strong disclosure. It explicitly states the node is deterministic, that inputs are processed transiently and 'not stored, logged, or retained', that browser mode returns a delegation URL, that gpu:true nodes always delegate, and that an AP2 artifact with execution_hash is exported. It also discloses the FV-status receipt is a snapshot, not a subscription. These traits go well beyond the readOnly/idempotent annotations and materially help an agent anticipate side effects and safety characteristics.

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 description is front-loaded with the most important execution facts, but it is verbose and repetitive, saying 'OpenChainGraph compute node' twice and including a long tail of URL and FV-status receipt metadata that is unlikely to help tool selection or invocation. Several sentences could be trimmed or moved to a manifest without losing agent-critical information.

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?

Given the annotations and 100% schema coverage, the description adds the key missing context: deterministic behavior, server vs browser execution semantics, transience, privacy constraints, and artifact export. It stops short of explaining the domain meaning of TMPG fails-charge or the expected shape of policy_parameters, but the schema and manifest reference cover much of that. Overall it is reasonably complete for invocation.

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 all four parameters. The description adds some execution-context meaning around compute modes and reinforces the synthetic/anonymized input constraint, but it does not meaningfully expand on parent_hashes, parent_tool_ids, or policy_parameters beyond what the schema provides. This meets the high-coverage baseline but does not exceed it.

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 labels the tool as 'TMPG Fails-Charge Recompute' and an 'OpenChainGraph compute node (compliance_control)', which points at the domain but never states in plain terms what a TMPG fails-charge recompute actually does or calculates. It gives execution architecture and output behavior, but the core purpose remains implied rather than explicitly described, and it does not differentiate itself from the many other recompute_* 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 description provides operational guidance such as compute:'auto' defaulting to server-side execution, compute:'browser' forcing client-side delegation, and 'Use synthetic or anonymised inputs only'. It does not, however, say when this tool should be chosen over related recompute or verification tools, nor does it specify any conditions that would make an alternative more appropriate.

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