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

Adds the single most important behavioral fact beyond the annotations: the tool has no side effects and opens nothing, it only returns instructions. It also explains why browser automation is required (DoorLoop's REST API is not self-serve), which preempts an agent trying to call the API directly. It does not describe the shape or detail level 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 essential facts (returns a guide, performs nothing, follow up with cotlet_browser_*) are present but buried mid-sentence after marketing filler ('from ChatGPT, Claude or any AI agent'). The API note is useful context but admits a dated check stamp that adds length without decision value.

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 tool with no output schema, the description covers purpose, side-effect profile, and the required follow-up tooling. Only the nature of the returned guide's format is left unspecified, which is a minor gap.

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?

Zero parameters, so there is nothing for the description to disambiguate and the baseline applies. The absence of any account/credential argument is implicitly covered by 'the user's own DoorLoop account'.

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?

States a specific verb+resource (list tenants in the user's DoorLoop account) and immediately disambiguates the real behavior: it returns a step-by-step guide rather than tenant data, and opens nothing by itself. That distinction is what separates it from the cotlet_browser_* siblings, though the name alone would mislead an agent into expecting records.

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?

Gives an explicit workflow: call this first to get the DoorLoop screen/button/field sequence, then perform it with cotlet_browser_* tools in the Cloud Browser. It does not name when to prefer alternatives such as cotlet_app_guide, so it stops short of full routing guidance.

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