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

Beyond the readOnly/idempotent annotations, the description discloses determinism, server- vs browser-side execution, transient processing with no retention, and that an AP2 artifact with execution_hash is exported. This is substantive behavioral context for a compute node and contradicts no annotation.

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 contains several distinct useful elements, but it repeats 'OpenChainGraph compute node' and includes a long URL and FV-status hash that are not needed for tool invocation. It is not poorly organized, but it is denser and less front-loaded than necessary.

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?

With no output schema, the description needed to explain what the classification returns; it only mentions exporting an AP2 artifact with an execution_hash. It also leaves policy_parameters fields undocumented, so an agent cannot know what inputs drive the bucketing. Compute mechanics are well covered, but domain semantics are missing.

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?

The schema already describes all four parameters with high coverage, so the baseline applies. The description adds some meaning around policy_parameters being computed server-side and the use of synthetic inputs, but it defers actual field names to an external manifest rather than clarifying the decision inputs.

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 name and opening line identify it as an FR 2052a inflow/outflow bucket classifier, so the subject and action are clear. However, the description never explains what classification it actually performs or how it differs from the many classify_* and compute_* siblings, and repeats 'OpenChainGraph compute node' without adding differentiation.

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 gives operational context: when to use compute modes and instructs to use synthetic or anonymised inputs only. It does not state when to use this tool instead of an alternative classifier or when not to use it, leaving selection to inference from the name.

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