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

The key behavioral trait is disclosed plainly: it 'opens nothing by itself', which matches readOnlyHint=true and destructiveHint=false in the annotations. It also states what the return content looks like (screens, buttons, fields). What remains unstated is what happens if the user is not signed into 17hats, which matters for a browser-handoff tool.

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 three sentences each carry distinct information: what it is, what it returns and does not do, and what tool family performs the action. The opening clause about ChatGPT, Claude or any AI agent is familiar boilerplate that could be trimmed, and the semicolon-chained phrasing is denser than ideal.

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 zero-parameter, non-destructive tool with no output schema, the description covers purpose, return content, and the follow-up tooling needed to actually complete the task. Preconditions such as an authenticated 17hats browser session are the main omission.

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, so the schema carries no semantics to explain and there is nothing for the description to compensate for. The baseline for a parameterless tool applies.

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 names a specific resource (17hats invoice) and explicitly corrects the impression created by the name: the tool returns a step-by-step guide rather than performing the send. That distinction from the cotlet_browser_* tools that actually execute the work is stated directly, though the phrasing 'Send invoice in the user's own 17hats account' in the first sentence briefly implies execution.

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 clear sequencing guidance: call this to get the steps, then perform them with cotlet_browser_* in the Cloud Browser. It also notes there is no official public API, which explains why the browser route is necessary. It does not explicitly contrast with siblings like 17hats_send_quote, but the workflow context is unambiguous.

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