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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior. The description adds genuinely non-obvious semantic context: a successful proof establishes membership only, not record truth or authorization to act. It does not cover error cases (e.g., digest not found in the tree), which keeps 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?

Two sentences, zero padding, with the core action front-loaded and the important semantic caveat immediately after. Every clause carries 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?

With no output schema and a nested optional query parameter, the description could say more about what the proof response contains (path elements, returned root) or how to handle a missing digest. It covers the interpretive caveat well but leaves the return shape and failure behavior unaddressed.

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 coverage is 100%, so the schema documents both parameters, and the description reinforces that the key input is a receipt digest. However, it adds no format, encoding, or syntax detail for the digest path segment or the optional query object, so it stays at the schema-driven baseline.

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 and resource: get Merkle audit inclusion evidence for a receipt digest. The scope is clear and the second sentence clarifies what the evidence does and does not mean, which distinguishes it conceptually from verification-style siblings, though no sibling is named directly.

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?

Usage is implied by the caveat that inclusion proves membership in the returned audit root, not truth or permission. There is no explicit routing to alternatives such as affix_merkle_verify_proof, affix_merkle_audit, or affix_merkle_root, so the agent must infer when to pick this tool.

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