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

Annotations already declare readOnlyHint=true and destructiveHint=false, and the phrase 'opens nothing by itself' is consistent with that, so there is no contradiction. The description adds real value beyond the annotations by disclosing what is actually returned (screens, buttons, fields) and that a separate browser session is required to effect changes. Rate limits and error behavior are not covered, but the key behavioral surprise is disclosed.

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 purpose, and no filler wording. The third sentence about JobSheet's API/Xero/Companies House is long and somewhat tangential, though it justifies why the browser route exists instead of a direct API call, so it earns partial keep.

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, non-destructive tool with no output schema, the description supplies the two things an agent needs: what comes back (step-by-step instructions) and what to do next (cotlet_browser_* tools). Nothing critical is missing, though a pointer to the sibling guidance tool would make it fully self-sufficient.

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 nothing for the description to disambiguate; the baseline for a parameterless tool is a 4. The description does not need to compensate for any schema gap here.

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 names a specific resource (job sheets in the user's own JobSheet account) and, crucially, reframes the tool's real job: it 'Returns how to do it in JobSheet step by step' rather than performing the listing itself. That correction of the misleading 'list' name lets an agent understand the tool immediately. The only minor deduction is that the opening sentence still reads like a data-fetching tool, with the true purpose buried in sentence two.

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 an explicit next step: 'then do it with the cotlet_browser_* tools in the user's JobSheet Cloud Browser', which tells the agent the tool is a first move in a browser workflow. It also states the negative condition 'opens nothing by itself'. It does not, however, distinguish this from the sibling cotlet_app_guide or explain when to prefer the dedicated jobsheet_create_* tools, so the routing is clear but incomplete.

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