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

Beyond the annotations (readOnly, idempotent, non-destructive), the description discloses concrete behavioral traits: results are newest-first, values are untruncated, an asin must belong to your own listings, and 'History may start after creation' plus 'no lifecycle deletions yet' set data-coverage expectations. These are non-obvious constraints that materially affect interpretation of results.

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?

Dense but front-loaded — the core action and result shape come first, then per-mode caveats. The telegraphic style ('sku: one seller listing...') is efficient, though it borders on shorthand that requires careful parsing.

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 10-parameter, no-output-schema read tool, the description covers return ordering, value fidelity, data coverage limits, and permission requirements per mode — enough to call and interpret it correctly. The main gap is that categories and changeTypes filter semantics are undocumented anywhere.

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 40%, so some compensation is warranted. The description does clarify the sku and asin parameters and their scope, but it is silent on categories, changeTypes, pageSize, and pageToken, and adds little beyond the schema for from/to/fields. Partial coverage of the 10 parameters keeps this at baseline-plus.

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 states a specific verb+resource — 'Field changes WisePPC observed' — plus ordering ('newest first') and payload shape ('old/new values untruncated'). It distinguishes the two lookup modes (sku vs asin) but does not differentiate itself from closely related siblings like get_events or get_mutations.

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 gives useful mode-selection guidance: sku for one seller listing on an amazon_sp target, asin for one catalog item that must belong to your listings. Permissions are named per mode. However, there is no explicit when-to-use or when-not-to-use guidance relative to sibling history/event tools, so alternatives are left implicit.

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