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

Annotations already mark this read-only, closed-world, and idempotent, so the safety profile is covered. The description adds the crucial behavioral fact that the tool performs no action itself and only returns procedural guidance, which the annotations cannot express. It stops short of describing the exact return shape (whether it is a numbered list, markdown, etc.).

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 – return a guide, then act via browser tools – is front-loaded in the first two sentences. The third sentence about the External API is tangential justification that could be trimmed, and the 'checked 6 Nov 2026' date adds noise rather than trust.

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 what matters: scope (the user's own account), non-execution, and the follow-on tool family. What the returned guide actually looks like is left implicit, which is the only meaningful omission.

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 there is nothing for the description to disambiguate. Baseline 4 applies; the absence of any parameter discussion is appropriate rather than a gap.

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 and title say 'Search tenders', but the body reveals it does not search at all – it returns a step-by-step how-to and 'opens nothing by itself'. That contradiction between the label and the actual behavior creates invocation risk. The description does state the real function, but only after the misleading opening framing.

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 clearly states the workflow: call this first to get screens/buttons/fields, then execute with the cotlet_browser_* tools in the Cloud Browser. It also pre-empts the obvious 'why not use the API?' question by noting EstimateOne's External API is not self-service and read-only. No explicit when-not or named sibling alternatives beyond cotlet_browser_*, so not a 5.

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