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

Annotations already declare readOnlyHint and openWorldHint, so safety is covered. The description adds genuinely non-obvious behavior: it consumes research quota (a cost signal an agent must budget for) and it does not persist/track the queried keywords, so no state is created. It does not say what happens on quota exhaustion or how unavailable keywords are reported.

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, no filler, with the core capability and the keyword cap front-loaded and the caveats (no tracking, quota cost) following immediately.

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 should convey the shape of the result, but it never says whether scores come back as a list, a map, on what scale (0-100? volume?), or how unknown keywords are represented. The quota-cost warning is valuable, but the return contract remains undocumented.

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 0%, so the description must carry the load, and it only does so partially: 'up to 100 keywords' maps to the terms maxItems and 'in a store' maps to the store param. It never explains that store is a two-letter code defaulting to 'us', nor the 200-character term limit, leaving both parameters explained only by the raw schema keywords.

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?

Specific verb implied + resource: retrieves popularity scores for keywords in a store, with the 100-keyword cap stated. The phrase 'without tracking them' distinguishes it from add_keywords and the other keyword-mutating siblings, though no sibling is named explicitly.

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 'without tracking them' clause implies the when-to-use case (one-off research vs. adding keywords to a project), and the quota note signals a cost tradeoff. But there is no explicit instruction on when to pick this over get_keyword_suggestions, get_keyword_history, or get_most_searched_keywords, all of which are equally plausible for popularity questions.

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