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

Annotations already mark this as read-only, and the description adds useful behavioral limitations: pure counting, no language detection, no reading-level or sentiment analysis, and no external retrieval. It does not cover edge cases like empty text or error handling, but for a simple read-only counter with an output schema, the disclosure is adequate.

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 tightly structured with clear labeled sections: what it does, when to use it, limitations, and alternatives. Each sentence earns its place, and the most important purpose information is front-loaded.

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 simple, read-only counting tool with one fully described parameter and an output schema, the description covers purpose, usage context, exclusions, and alternatives. Nothing needed to invoke it correctly is missing.

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 single 'text' parameter is fully described in the schema at 100% coverage, giving a baseline of 3. The description adds value by correcting the schema's misleading 'Text to summarize' phrase, clarifying that the text is raw content to be counted rather than semantically summarized. No additional parameter-level syntax is needed for such a simple input.

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 opens with a specific verb and resource: it returns counts of words, characters, sentences, paragraphs, and average words per sentence. It clearly separates this from semantic work by stating it 'counts only', and it names alternatives, distinguishing itself from web_search and http_fetch.

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 'Use when' section gives concrete examples—validating a summary length contract or comparing document sizes—and explicitly says not to use it for semantic summarization. The limitation note that it does not retrieve external content reinforces when web_search or http_fetch would be better choices.

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