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

Annotations already cover read-only, non-destructive, idempotent behavior, but the description goes well beyond them: credit cost (1 per lookup, +0.5 with history), free unknown seeds, the derived daily cap, paid-plan gating, 11-marketplace since-Aug-2026 harvest scope, and the caveat that positions are only comparable within one list. It omits any note on pagination or rate-limit error behavior, keeping it short of 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?

The resource and output shape are front-loaded, and the dense packaging of scope, routing, and cost is mostly earned. It is long and concatenated into single sentences, which slightly taxes scanning, but there is little 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?

With no output schema, the description still fully characterizes the return payload (per-list positions, observation timestamps, marketplaces, related vocabulary), the compare matrix mode, the history mode, and the cost/limit model. An agent has everything needed to call it correctly and set expectations.

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 baseline is 3, but the description adds real semantics beyond the schema: it explains what compare actually returns (the seed's primary list per marketplace plus a position matrix) and what history adds (every observation of each list as terms enter, leave, or move), which the terse schema descriptions do not convey.

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 opening states a specific verb+resource: Amazon autocomplete suggestion lists for a seed term, with precise output shape (one list per crawled prefix/department, position 1-10, first/last observed, marketplaces). It explicitly distinguishes itself from siblings keyword_rankings and product_keywords, so an agent can select it without opening any schema.

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?

The 'USE WHEN' clause enumerates concrete triggers (what buyers type, backend keyword language, product-research seeds, country differences) and the 'NOT' clause names two exclusions with the correct alternative tool for each. This is explicit when/when-not/alternatives routing.

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