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

Annotations already mark this readOnly, idempotent, and closed-world, but the description adds meaningful context beyond them: the tool 'opens nothing by itself' and returns a written walkthrough rather than performing any Workiz action. That is precisely the kind of side-effect disclosure that matters here. It still omits the exact return shape (single guide vs. multiple steps) and any limits on what Workiz screens it covers.

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 critical fact — that this returns instructions rather than data — should lead, but it arrives after a misleading first clause. 'from ChatGPT, Claude or any AI agent' is filler, and the closing paragraph on Workiz's REST API tiers is tangential although it does justify the browser-based route. Roughly half the text earns its place.

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 helper, the definition covers what it returns, that it performs no action, and which tools to chain next, which is what an agent needs. The main remaining gap is the tension between the tool's 'list jobs' framing and its guide-returning behavior, which is disclosed but not reconciled.

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 trivially complete, so there is nothing for the description to disambiguate. Baseline 4 applies; the description correctly refrains from inventing parameters.

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 opening sentence says it will 'List jobs in the user's own Workiz account', but the second sentence reveals the tool does not list anything: it 'Returns how to do it in Workiz step by step (screens, buttons, fields) and opens nothing by itself'. So the real purpose (emit an in-app procedure) is present but buried behind a contrary verb, and an agent skimming the first clause may expect job data back. The description does at least differentiate itself by pointing at the cotlet_browser_* family for the actual execution.

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?

There is a follow-up instruction ('then do it with the cotlet_browser_* tools in the user's Workiz Cloud Browser'), which is real routing guidance. However, there is no explicit statement of when to pick this over workiz_schedule_job or the other Workiz siblings, and no exclusions. The notes about the official API being Ultimate-plan-only imply why the browser route is preferred, but the agent must infer that.

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