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

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true and openWorldHint=false, so the safety profile is covered. The description usefully adds that nothing is opened or executed server-side and supplies API-availability context (no public API, webhooks or Zapier; only Xero and Companies House integrations, with a check date). It does not describe the shape of the returned steps or how to handle failures, so it adds moderate rather than substantial value beyond the annotations.

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?

Three sentences, front-loaded with the action and the key constraint ('opens nothing by itself'), followed by the handoff to browser tools and the justification for using a browser at all. The API-integration aside is slightly tangential but earns its place by explaining why no native integration exists.

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 guidance tool, the description covers everything needed: what it returns, what it explicitly does not do, which tools continue the workflow, and why an API path is unavailable. An agent could select and call it correctly without further information.

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 there is no per-parameter meaning to convey and the baseline applies. The description consistently implies a parameterless call by never referencing any inputs or options.

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 states the concrete end goal (create a quote in the user's own JobSheet account) and immediately clarifies what the tool itself does: returns step-by-step guidance for screens, buttons and fields and 'opens nothing by itself.' That resolves the tension between the imperative name and the actual read-only behavior, though the phrasing 'Create quote... Returns how to do it' takes a second pass to parse and sibling tools like jobsheet_create_invoice are not explicitly differentiated beyond the shared cotlet_browser_* follow-up.

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 a clear workflow: call this first to obtain the steps, then execute them with cotlet_browser_* in the JobSheet Cloud Browser. What is missing is the negative case — no mention of the related cotlet_app_guide or jobsheet_create_invoice alternatives, or what to do if the user has no JobSheet subscription.

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