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

Annotations already declare readOnlyHint/destructiveHint=false, so the safety profile is covered; the description earns credit by adding method (RAKE algorithm with per-language stopwords), automatic language detection, and the fact that the result includes scores and counts. It does not disclose rate limits or output structure in detail, but it adds real behavioral context beyond 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 first two sentences ('Keywords of a text (58 languages). Extract keywords.') merely restate the title and name with no added information, so nearly half the text is filler before the one informative sentence about the algorithm and output. The real content is front-loaded only after the redundancy.

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 characterize the return value; 'scores and counts' is a hint but not a clear picture of the response shape, so an agent must guess at the result format. Parameter and safety needs are otherwise covered, and the minor 58-vs-50+ languages inconsistency is a small blemish.

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 lang, text, limit, and max_words are already fully documented in the schema with ranges and defaults. The description's mention of auto language detection marginally reinforces the 'lang' parameter but adds no syntax or semantics beyond the schema, making the baseline 3 correct.

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?

States a specific verb+resource ('Extract keywords', 'key phrases and most frequent words') and names the mechanism (RAKE with language stopwords), which is enough to distinguish it from siblings like summarize or dictionary_define. It stops short of explicitly contrasting with those siblings, so it lands at 4 rather than 5.

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 description says it works on 'any text in 50+ languages' but gives no when-to-use guidance, no prerequisites, and never names an alternative (e.g. summarize when you need prose rather than keyword lists). Usage is only inferable from the verb.

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