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

Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds a genuinely non-obvious trait: the tool returns guidance rather than mutating anything, and returns UI-level steps (screens, buttons, fields). It also explains why browser automation is required (no public API, no webhooks). Minor noise remains, such as the oddly dated API check.

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 purpose and the follow-up action are front-loaded, which is good, but the trailing sentence about Joist's API status ('checked 26 Oct 2026', 'help center and pricing page document none') is verbose justification that only weakly supports the agent's decision. It could be compressed to a clause about the lack of API.

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, no-output-schema tool, the description covers what the result looks like (step-by-step screens/buttons/fields), that it performs no side effects, and what to do next. The only residual gap is ambiguity versus similarly named siblings.

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 baseline is 4 and the schema fully covers the (empty) input object. The description adds nothing parameter-related because there is nothing to describe.

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 definition does eventually state the real output — 'Returns how to do it in Joist step by step (screens, buttons, fields)' — but the opening clause 'Record payment in the user's own Joist account' reads like the tool performs the payment, which it does not. The tension is only partially resolved inside the same sentence, and nothing distinguishes it from the unprefixed sibling 'record_payment'.

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 explicit workflow context: the tool 'opens nothing by itself', and the actual action is performed afterward with the 'cotlet_browser_* tools'. That is a clear when-to-use / what-to-do-next statement. It stops short of excluding alternatives (e.g., when to pick this over the sibling 'record_payment' 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.