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

Annotations already establish readOnly, idempotent, non-destructive, closed-world behavior. The description adds useful context that the tool returns screens, buttons, and fields and performs no action itself, preventing the agent from expecting direct invoice data. It does not cover auth or rate limits, but those are less relevant for a read-only guide 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 core instruction is in the second sentence, but the first sentence includes generic 'ChatGPT, Claude or any AI agent' filler and the final API sentence is largely irrelevant to invoking this guide tool. The structure also buries the actual behavior of returning instructions behind a misleading 'List unpaid invoices' opener.

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, read-only guide tool with rich annotations and no output schema, the description explains the expected output type (step-by-step screens, buttons, fields) and the required follow-up browser tools. It is nearly complete, though the ambiguity between listing and instructing keeps it from being fully airtight.

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?

There are zero parameters, so the schema is trivially complete and the description need not document parameter semantics. The description adds no parameter detail, which is acceptable for a no-argument tool.

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 opens with 'List unpaid invoices' but then says it 'Returns how to do it in Alegra step by step' and 'opens nothing by itself,' so the actual deliverable is procedural guidance rather than invoice data. It identifies the resource and account scope, but the name/title and first sentence create ambiguity about whether the tool lists invoices or instructs the agent. Sibling differentiation is partial: it points to cotlet_browser_* for execution but does not distinguish from alegra_* alternatives.

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 explicitly tells the agent to use this tool to get steps and then execute with cotlet_browser_* tools in the Alegra Cloud Browser. It does not provide when-not-to-use conditions or compare against alegra_create_invoice or alegra_record_payment, but the sequencing guidance is clear.

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