Text-Toolkit

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. 'Count words in text' implies a read-only operation that returns a numeric result, but it doesn't specify output format (e.g., integer count), handling of edge cases (e.g., empty strings, punctuation), or performance characteristics. For a tool with zero annotation coverage, this is a significant gap in transparency.

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 extremely concise at three words, with zero wasted language. It is front-loaded with the core action ('Count words'), making it easy to parse. Every word earns its place by directly contributing to understanding the tool's function.

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?

Given the tool's simplicity (1 parameter, no annotations, no output schema), the description is incomplete. It doesn't explain what constitutes a 'word', how the count is returned, or handle edge cases. While minimalism can be appropriate, this lacks basic context needed for reliable use, especially with siblings that perform similar operations.

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 input schema has 1 parameter with 0% description coverage, so the schema provides no semantic information. The description adds minimal value by implying the 'text' parameter is the input to count words from, but it doesn't elaborate on constraints (e.g., max length, encoding) or examples. This meets the baseline for low schema coverage but doesn't fully compensate.

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 'Count words in text' clearly states the verb ('Count') and resource ('words in text'), making the purpose immediately understandable. It distinguishes from siblings like count_characters and count_lines by specifying 'words' rather than characters or lines. However, it doesn't explicitly mention what constitutes a 'word' (e.g., whitespace-separated tokens), leaving some ambiguity.

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 no guidance on when to use this tool versus alternatives. It doesn't mention sibling tools like count_characters or count_lines, nor does it specify use cases (e.g., for text analysis vs. formatting). Without any context on when this tool is appropriate, the agent must infer usage from the name alone.

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