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

Annotations declare readOnlyHint=true and destructiveHint=false; the description is consistent with that, explicitly saying it 'opens nothing by itself' and only returns guidance. That non-obvious disclosure is exactly what an agent needs, since the tool name implies a mutation. The note that Sunsama has no documented public API further explains why browser automation must follow. It stops short of describing the guide's structure beyond 'screens, buttons, fields'.

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 'opens nothing by itself' clarification is buried in the second sentence behind a misleading imperative. 'from ChatGPT, Claude or any AI agent' is marketing filler, and 'Sunsama's official API: Sunsama has no documented public API' is redundantly phrased. The definition is compact but not well front-loaded.

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, non-destructive guidance tool with no output schema, the definition covers what matters: what it returns, that it is inert, and what to do next. The remaining gap is how the agent supplies task identity, which the description leaves to inference.

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?

There are zero parameters, so the schema carries no semantic burden and the baseline is 4. The description does not need to explain parameters, though it is silent on how the agent is expected to convey which task and subtask it means, which must come from conversation context.

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 does specify the resource (Sunsama subtask) and the actual mode of operation: it returns step-by-step instructions rather than performing the action. The lead verb 'Add subtask' is misleading on its own, since the tool only produces a guide, but the second sentence corrects that. It does not name or differentiate itself from sibling cotlet_app_guide or sunsama_create_task.

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 usage pattern: call this first, then execute the steps with the cotlet_browser_* tools in the Sunsama Cloud Browser. That is a concrete when-to-use context. However, it never says when NOT to use it, nor names cotlet_app_guide as the alternative for non-Sunsama apps.

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