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

Annotations already declare readOnlyHint=true, idempotentHint=true and openWorldHint=false, and the description is consistent with them by stressing that nothing is opened or changed. Beyond that it adds the rationale for the browser-based approach (no official API) but says nothing about what the returned instructions look like in practice or how long they are.

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 message (returns steps, opens nothing, use the browser tools afterwards) is front-loaded, but the opening clause about ChatGPT, Claude or any AI agent is audience framing that does not help tool selection, and the '(checked 11 Oct 2026)' aside adds noise. The semicolon-joined sentence mixes the deliverable and the next-step guidance awkwardly.

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 covers what is returned (screens, buttons, fields) and what the agent should do next, which is sufficient to call it correctly. The only gap is the absence of a stated prerequisite such as an authenticated Crexi session in the Cloud Browser.

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, so the schema baseline would be a 4. However, the description never states that no input is required or whether the account/target property is implied, leaving the agent to infer that the call is parameterless from the empty schema alone.

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 resource and verb ('Get comps in the user's own Crexi account') and then clarifies the actual deliverable: a step-by-step walkthrough of screens, buttons and fields rather than comp data itself. It separates itself from data-returning siblings by pointing at the cotlet_browser_* tools, though the name 'get_comps' still mildly oversells what comes back.

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 explicitly says the tool 'opens nothing by itself' and that the agent must then perform the steps with the cotlet_browser_* tools in the Crexi Cloud Browser, which is actionable routing guidance. It also justifies why this is the path at all (no public Crexi API), though it does not state any precondition such as the user having a Crexi account configured.

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