util_token_estimate

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

Discloses the two estimation heuristics explicitly, giving agents insight into the algorithm. Without annotations, this carries the behavioral burden. Could mention output format or edge cases, but the core behavior is transparent.

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?

Single sentence, 25 words, front-loaded with purpose and heuristics. No extraneous information. Every word earns its place.

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?

The tool has a simple function but the description omits how to provide input and what the output looks like (no output schema). Agents lack enough context to invoke it correctly without guessing the 'arguments' structure.

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 only parameter 'arguments' is a vague object with no description in schema or tool description. The description does not mention how to input the text. With 0% schema coverage and no param info, this is a critical 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?

Clearly states what the tool does: 'Estimate token count for text.' It specifies the two heuristics (word/4 for GPT-family, char/4 for Claude-family), making the purpose unambiguous. Among many sibling utilities, this one is distinct in function.

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?

No guidance on when to use this tool versus alternatives. Does not explain when to choose GPT vs Claude heuristic, nor provides context for appropriate use. Lacks any 'when to use' or 'when not to use' information.

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