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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds genuinely non-schema context: it is a paid call ($0.75 USDC on eip155:8453 to a specific payTo address), which is important behavioral information. It stops short of describing trail semantics such as ordering, hash-chain verification via prev_hash/expected_head, or result size.

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?

It is short but badly front-loaded: the first thing an agent reads is a chain identifier, a hex payTo address, and a price, ahead of any statement of function. The run-on semicolon syntax and mixed fragments ('an object with 77 fields including action, actor') read as assembled strings rather than prose.

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 seven optional parameters, an output schema, and a hash-chain concept implied by prev_hash/expected_head, the description leaves key behavior unexplained: whether the trail is paginated, whether expected_head enforces chain integrity, and what as_of reproduction entails. The output schema excuses explaining return fields, but the semantic gaps around the chain parameters remain.

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 seven parameters are already documented at baseline quality. The description adds no parameter-level meaning (nothing on actor, as_of, steps, run_id, prev_hash, or expected_head) and does not explain how they combine, so it neither helps nor hurts beyond the schema.

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 never states in a clean sentence that it retrieves a decision trail; the closest evidence is the fragment 'for trail, not permission audit' plus 'an object with 77 fields including action, actor'. It does gesture at the resource and the return payload shape, but the purpose is buried behind payment routing details, so an agent must infer the verb from the tool 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?

'use it rather than `agent_permission_audit` for trail, not permission audit' explicitly names one alternative and the condition that selects it, which is real routing guidance. However, no other when/when-not guidance is given despite ~150 siblings, and the phrasing is clipped enough to require interpretation.

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