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

Annotations already mark the tool readOnly and idempotent; the description adds genuinely useful behavioral detail by revealing that each item returns its own receipt and the batch receipt id is a sha256 over sorted item receipt ids. This explains deterministic output/reference behavior beyond the annotations.

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?

Two dense sentences with the key detail ('up to 50 computes', per-item receipts, batch hash) front-loaded. Every sentence adds information and there is no filler.

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 tool with a nested items array, formula enum, and no output schema, the description covers the essential output/citation semantics without explaining error behavior. It is complete enough for correct invocation, though a note on partial failures or per-item validation would make it fully robust.

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?

With 0% schema description coverage, the description partially compensates by explaining that items are computes, up to 50, and each yields a receipt. It does not, however, break down the required formula/inputs structure, leaving the agent to infer those from the schema field names and sibling tools.

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 batch operation: run up to 50 computes in one call for grids/sensitivity tables. The description distinguishes the tool from single-compute siblings (canon_compute) by emphasizing batching and the single hash for a whole table.

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?

Describes when to use it: scenario grids and sensitivity tables requiring many computes. It does not explicitly name canon_compute as the alternative for a single compute, but the guidance is clear enough for an agent to pick the right tool.

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