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

Annotations already declare readOnly, idempotent, non-destructive, and closed-world, so the safety profile is covered. The description does add genuine behavioral context beyond that: transient processing with no storage or logging, a synthetic-data-only constraint, and an AP2 artifact export carrying execution_hash for provenance. However, the surrounding URL and FV-status receipt text is boilerplate that dilutes rather than informs.

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 sentences that matter (compute modes, transient processing, artifact export) are buried among redundant 'Deterministic OpenChainGraph compute node' repetition, a documentation URL, and an offline-receipt disclaimer about a snapshot file. Substantial text is spent on vendor metadata rather than tool-specific 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?

For a compute node with no output schema, the description should convey what the computation produces and how to populate policy_parameters. It covers the execution environment and provenance reasonably but leaves the actual analytical function and the field names of the primary input undocumented.

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 compute, parent_hashes, parent_tool_ids, and policy_parameters fields are already documented in the schema, and the description largely restates the compute-mode semantics. Critically, for the only substantive input it says 'See the tool's manifest for field names', deferring documentation outside the tool definition rather than adding meaning.

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 an 'OpenChainGraph compute node (analytics_mandate)' and repeats that it is 'deterministic', but never says what a consultation response tracker computes or what question it answers. An agent reading only this text cannot distinguish its analytics function from the dozens of other compute_* siblings beyond the opaque name.

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?

It explains compute-mode selection ('auto' vs 'browser' vs gpu:true delegation), which is invocation mechanics, not when to choose this tool over alternatives. There is no statement of preconditions, suitable inputs, or which sibling tools compete with it.

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