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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, not open-world), so the bar is lower. The description does add real value by clarifying that no browser action happens here and by stating Joist has no public API or webhooks (so the browser path is the only one). However, it doesn't say whether a Joist session/login must already exist before the browser tools will work, which matters for a workflow that depends on an authenticated session.

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 — steps only, no action, then use browser tools — is front-loaded and well placed, but the third sentence about the absence of a public API (including the 'checked 26 Oct 2026' date) is padded and reads like justification rather than guidance. Tightening would make the routing clearer.

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 no-param, no-output-schema guide tool this is close to adequate: it explains what is returned and what to do next. It falls short on prerequisites (account/session state) and on differentiating itself from the similarly named sibling that presumably returns actual invoice data.

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?

Zero parameters with 100% schema coverage, so there is nothing for the description to disambiguate. It correctly implies the tool is parameter-free by describing it as account-scoped with no inputs. Baseline of 4 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 opens with 'List invoices in the user's own Joist account,' which suggests data retrieval, but then says it 'Returns how to do it in Joist step by step (screens, buttons, fields) and opens nothing by itself' — an instructions/guide tool. The verb+resource framing is specific, but the tool's actual output contradicts the name's implication, so an agent could easily pick it expecting invoice data. It also never distinguishes itself from the sibling 'list_invoices'.

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 follow-on routing: use the cotlet_browser_* tools in the user's Joist Cloud Browser after reading the steps, and notes this tool itself opens nothing. That is actionable when-to-use context. What's missing is an explicit statement of when to prefer this over the plain 'list_invoices' sibling.

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