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

Annotations already cover read-only/idempotent/no-open-world, yet the description still adds real behavioral context: cache-first resolution, a possible single cached store check, a bounded daily allowance, and the guarantee it never consumes a monthly run. It also states execution location and that no AI or store access is needed client-side, which an agent cannot infer from the annotations.

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 core purpose is front-loaded in the first sentence and the cost/execution caveats follow in a logical order with no filler. The dense parenthetical letter codes (A, R, Rt, T, Q, B, L, C, E) are cryptic in isolation and slightly bloat the first sentence, keeping it short of a 5.

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 does the right thing by naming what comes back (scores plus top apps and store suggestions) and by explaining the cost model for a tool that can trigger a store check. What is missing is any sense of the response shape or how the 0-100 indexes relate to the returned apps, which an agent would need to use results well.

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 all five parameters are already documented; the description's contribution is limited to implying that relevance is scored against an application ('relevance to an application'), which loosely maps to application_id. It adds no format or default guidance beyond what the schema provides, so baseline 3 applies.

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 uses a specific verb ('Explain') plus a precisely scoped resource ('one keyword's Wow Keywords scores') and enumerates the four score families (popularity, difficulty, relevance, opportunity) with their sub-components, so an agent can distinguish it from report-style siblings like wow_keywords_report. It never names a sibling tool, though, so the differentiation is inferential rather than explicit.

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 'Explain one keyword' (single-keyword drill-down vs. bulk report), and the cost sentence ('answered from the cache when possible... never spends a monthly run') gives an implicit preference rule for cheap lookups. There is no explicit 'use this instead of X' routing against wow_keywords_get, wow_keywords_report, or inspect_keyword, which is the main gap given how many closely related siblings exist.

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