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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, and the description usefully reinforces this with 'opens nothing by itself', which is the single most important thing an agent must know before calling a tool named 'send_invoice'. It also discloses the return shape (step-by-step screens/buttons/fields) and the plan-gating of the official API, adding context the annotations cannot carry. It does not describe output length or failure modes if the user lacks the feature.

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 operational core ('opens nothing by itself; then do it with cotlet_browser_*') is buried in the middle of a long second sentence rather than front-loaded. 'from ChatGPT, Claude or any AI agent' is filler, and the API/plan sentence is lengthy for a side note, though it does convey a real constraint.

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 no parameters, no output schema, and annotations covering the safety profile, the definition supplies what an agent needs: what is returned, that nothing is executed, and which tools to use next. Only the caveat about what happens if the user's plan or UI differs is absent.

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 schema has zero parameters, so there is nothing for the description to disambiguate and the baseline of 4 applies. The description's implicit contract that all invoice specifics are gathered from the returned steps rather than inputs is consistent with the empty schema.

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 second sentence is explicit that the tool returns step-by-step guidance (screens, buttons, fields) rather than performing the send, which distinguishes it from the cotlet_browser_* executors. The opening clause 'Send invoice in the user's own Contractor+ account' reads like an action verb and briefly reinforces the misleading impression created by the tool name, so an agent must read past the first sentence to understand it is a guidance/read tool.

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 clearly prescribes the workflow: call this to get the steps, then execute them with the cotlet_browser_* tools in the Contractor+ Cloud Browser. It also explains why the official API is not an option for most plans, which heads off a plausible wrong path. It stops short of naming when NOT to use this versus siblings like contractor_plus_send_estimate or cotlet_app_guide.

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