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

Annotations already declare readOnlyHint, destructiveHint=false, and idempotentHint, so the safety profile is covered structurally. The description adds one genuinely useful behavioral fact beyond that — it performs no action and returns a step-by-step guide — but then spends a sentence on Jobber's GraphQL API registration status, which is background rather than behavior of this tool. No guidance on the shape or size of the returned guide.

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-on instruction come first, which is good front-loading. However, the closing sentence about Jobber's official GraphQL API ('checked 14 Oct 2026... registering an app') is tangential to invoking this tool, and 'from ChatGPT, Claude or any AI agent' is boilerplate. Roughly a third of the text does not help the agent act.

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 guide tool with no output schema, the description supplies what matters: it states the return is step-by-step UI instructions and points at the browser tools that execute them. The only real gap is that it never says what context the agent should gather first (e.g., which quote) before the guide is actionable.

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, which sets the baseline of 4. The description does not contradict that, but it also doesn't explain the consequence — that the quote in question must be identified later by the browser tools rather than passed here. That is a minor omission rather than a documentation gap in a schema sense.

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 operation and immediately redefines it: it does not convert the quote itself, it 'Returns how to do it in Jobber step by step (screens, buttons, fields) and opens nothing by itself.' That clarification resolves the mismatch with the `convert_quote_to_job` name. It does not, however, distinguish itself from jobber_* siblings such as jobber_create_quote, leaving the agent to infer whether those act directly or also just guide.

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?

The description gives clear sequencing: call this first to get the steps, 'then do it with the cotlet_browser_* tools in the user's Jobber Cloud Browser.' That is real when-to-use guidance tied to a named follow-on tool family. It stops short of exclusions — nothing says when this tool is unnecessary or what to do instead if the user wants a different jobber_* operation.

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