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

Goes well beyond the readOnlyHint annotations by disclosing that the tool 'opens nothing by itself' and returns descriptive guidance (screens, buttons, fields) rather than data — critical for an agent that might otherwise expect a list. It also records that Crexi has no public API, explaining why the browser route is required. Minor gap: it doesn't say how large the returned guide is or whether the saved-search list is included in the output.

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?

Compact and front-loaded on the resource, but the second sentence crams three separate ideas (return format, non-action, follow-up tools) into one clause chain. The trailing 'Crexi's official API: Crexi has no public API (checked 11 Oct 2026)' is awkwardly formatted and its future-dated check timestamp raises more questions than it answers.

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 guidance tool, the description covers the essential context: it does not mutate anything, it returns instructions, and it must be paired with the cotlet_browser_* tools. What's missing is any hint of the shape or length of the returned guide, which an agent would need to plan the follow-up browser steps.

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 baseline of 4 applies; there is nothing for the description to disambiguate. The description correctly implies no input is needed beyond the authenticated Crexi session.

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 a specific resource (saved searches in the user's Crexi account) but then reveals the tool does not actually return the searches — it returns step-by-step instructions on how to find them. That mismatch with the name 'List saved searches' is disclosed, but the agent must read the second sentence to understand what the tool really does. It does not distinguish itself from cotlet_app_guide, which appears to serve a similar guide-providing role.

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 clear forward routing: use this first, then execute with cotlet_browser_* tools in the Crexi Cloud Browser. However, no when-not guidance is given, and the overlapping sibling cotlet_app_guide is never mentioned as an alternative or prerequisite. The workflow is implied rather than spelled out as an ordered procedure.

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