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

Annotations already declare readOnlyHint, openWorldHint=false, idempotentHint and destructiveHint=false, so the safety profile is covered. The description contributes a genuinely useful behavioral fact — 'opens nothing by itself' — and explains the no-public-API constraint that motivates the browser workaround. It does not describe the shape or length of the returned instructions, whether they are stable across calls, or any required account/auth state.

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 core sentence is a run-on that chains the return value, a non-action disclaimer, and an instruction for subsequent tool use with semicolons and an unclear 'it'. The 'from ChatGPT, Claude or any AI agent' clause and the dated API-check parenthetical consume space without helping an agent decide or act. The most decision-relevant fact (that this returns instructions, not data) is not 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?

With zero parameters and no output schema, the description carries the burden of explaining what comes back, and it only says 'step by step (screens, buttons, fields)' without describing the result structure or whether it is a prerequisite to a specific browser sequence. It does convey the account scope and the 'no public API' rationale. For a guidance-emitting tool, an agent still has to guess how to translate the returned steps into browser calls.

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 tool takes zero parameters and the schema coverage is 100%, so there is no parameter meaning the description needs to supply. Baseline 4 applies; nothing is missing because nothing is accepted.

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 opening sentence restates the tool name ("List biometrics in the user's own Cronometer account"), and only the second sentence reveals the actual behavior: it returns step-by-step instructions rather than the biometric data itself. That distinction matters a lot for tool selection, but it is buried mid-sentence in a run-on, so an agent could still expect a data payload. The verb+resource are at least named, and 'biometrics' differentiates it from diary/food siblings.

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?

It gives a follow-on path ("then do it with the cotlet_browser_* tools") and warns that it opens nothing by itself, which implies the browser tools are the alternative for actually performing the action. However, it never states when to call this versus other Cronometer read tools like cronometer_get_diary_day or how it relates to cronometer_log_biometric. Usage is inferred rather than prescribed.

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