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

The description is consistent with the annotations (readOnlyHint=true, destructiveHint=false) and reinforces them with the concrete claim that the tool 'opens nothing by itself,' which is exactly the behavior an agent needs to know to avoid assuming a change order was actually created. It also discloses the account context ('the user's own Buildertrend account') and where the subsequent action happens. It does not cover auth requirements or whether an active browser session must exist first.

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 first clause largely restates the name, and the trailing note about Buildertrend's Marketplace integrations and 'checked 11 Oct 2026' is dangling context that does not help the agent call the tool. The important behavior ('returns steps, opens nothing') is present but not front-loaded ahead of the redundant framing.

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 guidance tool with no output schema, the description covers what it returns (screens, buttons, fields), what it does not do (opens nothing), and what to use next (cotlet_browser_*). Nothing essential for calling it correctly is missing, though it never states prerequisites such as whether a Cloud Browser session must already be open.

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 input schema takes zero parameters, so the baseline is 4. The description introduces no parameter discussion, which is appropriate here since there is nothing to parameterize.

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 name suggests a write operation, but the description corrects that: it explicitly states the tool 'Returns how to do it in Buildertrend step by step (screens, buttons, fields) and opens nothing by itself.' That is a specific, distinguishing purpose, and it is separated from the actual work done by the cotlet_browser_* tools. The lingering mismatch between the 'create' verb in the name and the advisory nature of the output leaves a small ambiguity.

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 clear implied workflow: call this first to get the screens/buttons/fields, then execute with cotlet_browser_* in the user's Buildertrend Cloud Browser. However, it gives no explicit when-not-to-use guidance and does not name the obvious alternative, cotlet_app_guide, which sounds like it serves a similar guidance role. Usage is inferable but not routed.

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