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

Annotations declare readOnlyHint=true, and the description earns credit for explaining why: 'opens nothing by itself' and returns instructions only, pre-empting a costly misinterpretation given the 'create' name. It adds return-content detail (screens, buttons, fields) beyond the annotations. It stops short of stating auth/session prerequisites for the Yardi Cloud Browser or failure behavior when no session exists.

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 purpose and the non-mutating caveat are front-loaded, which is good, but 'from ChatGPT, Claude or any AI agent' is promotional filler and the closing note on Yardi's API availability is tangential detail. Both sentences could be cut without losing operational meaning.

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 tool with no output schema and safety fully covered by annotations, the description supplies the essential missing piece: what actually comes back and what to do next. Missing only the preconditions (existing Yardi Cloud Browser session) and the fact that no arguments are expected.

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?

With zero parameters the schema carries nothing, so the description is the only place semantics could live. It does not say that no inputs are required or what work-order details (property, unit, issue) the agent must already hold to make the returned steps useful, leaving a small but real gap for a parameterless tool.

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 resource (work order in the user's Yardi account) and, crucially, clarifies that the tool itself returns a step-by-step procedure rather than performing the write. It also names the sibling family (cotlet_browser_*) that performs the actual action, so an agent can distinguish it. The only blur is the opening phrase 'Create work order', which briefly implies mutation before being corrected.

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 to obtain the Yardi screens/buttons/fields, then execute with cotlet_browser_* in the Cloud Browser. That is actionable when-to-use context with a named follow-on. It does not explicitly contrast with yardi_update_work_order or say what to do if the user lacks a Yardi session.

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