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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered structurally. The description adds genuinely useful context beyond that: it returns procedural guidance rather than performing the action, requires a Cloud Browser session to complete, and explains why the official API is not an alternative. It stops short of describing the shape of the returned steps beyond 'screens, buttons, fields' or failure modes if the user lacks a browser session.

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 critical fact — it returns instructions and opens nothing — is front-loaded in the first sentence, and the follow-up browser instruction is actionable. The closing sentence about EstimateOne's External API is somewhat tangential and the 'checked 6 Nov 2026' date stamp adds noise, but it does preempt a plausible agent question.

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, annotation-covered, no-output-schema tool, the description covers the essentials: what it returns, that it is non-acting, and what must happen next. Naming the sibling it supersedes or describing how the returned steps are formatted would close the remaining 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?

The tool takes zero parameters, so there is no schema semantics to compensate for; the baseline of 4 applies. The description correctly implies the tool needs no input because targeting context comes from the user's own account and the subsequent browser calls.

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 the resource (project package) and the target context (the user's own EstimateOne account) and explicitly corrects the misleading name by stating it returns step-by-step instructions and 'opens nothing by itself'. What is missing is a direct contrast with the closest sibling, estimateone_download_project_package, so an agent must infer the boundary between requesting and downloading.

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 gives a clear operational path: read the returned steps, then execute them with cotlet_browser_* tools in the user's EstimateOne Cloud Browser, and it notes the External API is not a self-service read-only option. It does not say when an agent should prefer the sibling download tool instead, which is the main remaining gap.

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