Record consumer chat (estimated)

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

With no annotations, the description does well by disclosing token estimation via BPE proxy, the tagging as 'estimated', the two input modes, and the model default. It does not mention failure behavior or side effects, but for a logging tool this 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?

Three sentences, front-loaded with purpose, no wasted words. Every sentence adds value (purpose, preferred input, fallback, estimation detail).

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 complexity (estimation, two input modes, optional params) and no output schema, the description covers the key aspects. Minor gap: behavior when both turns and page_text are provided is unspecified, and conversation_id is not explained. Otherwise complete.

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 75% (3 of 4 params described), and the description adds significant meaning by explaining the two input methods (preferred vs fallback) and estimation behavior. The conversation_id param lacks description in both schema and description, but overall value is above baseline.

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 it records estimated usage for Claude web chats, distinguishes between structured turns and fallback page_text input, and mentions token estimation. This is specific and distinct from sibling tools that analyze or score data.

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?

Provides clear context on when to use (for conversations without token counts) and gives a preferred method with a fallback. However, no explicit when-not-to-use or alternatives are named.

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