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

The annotations declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, and the description actively reinforces this with 'opens nothing by itself' — so an agent cannot mistake it for a real write. It adds context the annotations cannot convey: the return payload is step-by-step UI instructions and the actual mutation must happen through the browser tools. It does not state rate limits or whether the steps are cached, but nothing here is misleading.

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 correction that matters most, followed by the workflow hand-off and the justification for that workflow. The parenthetical '(screens, buttons, fields)' and the dated API check are dense and earn their space. Opening with the imperative 'Create job in the user's own Tradify account' briefly restates the misleading name before the correction lands, which is a small structural wart.

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 zero parameters and no output schema, the description must itself say what comes back, and it does — step-by-step screens, buttons and fields — plus what does not happen (no side effects) and what to do afterward. The only gap is the shape of the returned guidance (numbered steps vs. a script of tool calls), which an agent might want to know before parsing the response.

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 and the schema is closed (additionalProperties: false), so there is no parameter meaning to add or compensate for. Baseline 4 applies; the description correctly implies no inputs are needed because the call only produces instructions.

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 the resource (a Tradify job) and, crucially, corrects the misleading name by stating the tool 'Returns how to do it in Tradify step by step (screens, buttons, fields) and opens nothing by itself.' That makes the actual function — a guidance generator, not a mutator — unambiguous. It does not differentiate itself from the sibling create_job or cotlet_app_guide, which is the only thing keeping it from a 5.

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 execution path: call this first, 'then do it with the cotlet_browser_* tools in the user's Tradify Cloud Browser,' which tells the agent exactly what to do next. It also explains the rationale (no official API, docs, or webhooks as of 11 Oct 2026), pre-empting an attempt to find a native endpoint. It stops short of stating when to prefer cotlet_app_guide or the plain create_job sibling instead.

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