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

No annotations are provided, so the description carries the full burden. It discloses the scoring algorithm ('TF scoring') and the return structure ('keywords: [{word, score}], total_words'), which are behavioral details beyond a simple action statement. However, it doesn't mention edge cases like stopword removal or handling of empty text, so it's not exhaustive but still informative.

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 description is concise with two sentences: the first states the action and method, the second lists the return format. Every word earns its place with no fluff or repetition, and it front-loads the most important information first.

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 low-complexity tool with no output schema, the description provides the return structure directly, which is helpful. It covers what the tool does, how it works, and what it returns. Missing are any notes on parameter semantics and potential limitations, but the overall context is sufficient for a simple extractor tool.

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?

The schema has 0% description coverage, so the description must compensate. It only implicitly references the 'text' parameter via 'from text' and does not explain 'top_n' at all. The parameter name 'top_n' is somewhat self-explanatory, but the description fails to clarify how it affects the output or that it defaults to 10, leaving a clear gap.

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 clearly states the verb 'Extract' and the resource 'top keywords from text', and defines the method 'using TF scoring'. This distinguishes it from siblings like analyze_sentiment or summarize_text, which have different actions and outputs.

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 provides clear context: use this tool when you need to extract keywords from text based on term frequency. It doesn't explicitly mention alternatives or exclusions, but the behavior is straightforward and the sibling names suggest distinct use cases, so the guidance is adequate.

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