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

Annotations already cover readOnly/idempotent/non-destructive, and the description adds real behavioral context beyond them: transient processing with no storage, logging, or retention, a 'use synthetic or anonymised inputs only' constraint, server-vs-browser delegation behavior, and the chained artifact it consumes and emits. Missing specifics on failure modes and permission requirements keep it from a 5.

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 purpose is front-loaded, but the prose is dense and partly redundant ('OpenChainGraph compute node' repeated twice) and the trailing artifact-URL and FV-status receipt text adds length without clarifying invocation. It is serviceable rather than tight.

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-value explanation is not required, and the description still covers compute modes, data-handling policy, upstream artifact consumption, and chain provenance. For a 4-parameter compute/export node this is close to complete, with only failure and permission behavior left implicit.

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 all four parameters (compute, parent_hashes, parent_tool_ids, policy_parameters) are already documented in the schema. The description restates the compute-mode behavior but adds no syntax, ordering, or format detail beyond the schema, so the baseline of 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?

States a specific verb+resource (publish the Model Risk Head) and describes the mechanics: an OpenChainGraph compute node that exports an AP2 artifact with execution_hash for chain provenance. It does not, however, differentiate itself from close siblings such as publish_index_head, publish_market_mark_head, or emit_chaingraph_artifact, so an agent cannot tell which publish head to pick from the description alone.

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 compute mode semantics are spelled out (auto/server/browser, gpu:true always delegates), which gives usage context, but there is no explicit when-to-use / when-not-to-use guidance and no routing to alternative tools. The agent must infer that this specific head is the right one among many publish_* and emit_* siblings.

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