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

Annotations already declare this a safe, idempotent read, so the bar is lower. The description adds genuine behavioral context on top: the return payload ('counts and percentages') and the fact that stopword filtering is English-only and configurable.

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?

Three short sentences, front-loaded with what it does and what it returns. The final 'useful for' sentence is the weakest but still contributes selection context rather than padding.

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 four-parameter read-only analysis tool with an output schema and full annotation coverage, this is close to sufficient: purpose, return shape, and the stopword option are all covered. Only the min_length parameter goes unaddressed, and the schema handles it.

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% with per-parameter descriptions and a worked example, so the schema carries the load. The description echoes 'top N' and 'stopword filtering' without adding syntax or defaults, and says nothing about min_length, so it earns the baseline rather than more.

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 and resource ('Analyze word frequency in text') and adds the shape of the result ('top N words with counts and percentages'). It doesn't explicitly differentiate itself from the nearby text_stats or count_tokens siblings, so it falls short of a 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 closing list ('content analysis, keyword extraction, and LLM output analysis') implies when to reach for it, which is real guidance. But there is no explicit when-not and no routing away from text_stats or count_tokens, which are the obvious alternatives in this sibling set.

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