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

Annotations already declare readOnly, idempotent, non-destructive and closed-world; the description adds the non-obvious fact that the tool performs no action and only returns procedural guidance, plus the API plan limitation. That is genuine context beyond the structured fields, though it says nothing about step granularity, length, or failure modes.

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 key clarification ('opens nothing by itself') is buried mid-sentence inside an awkward construction: 'Returns how to do it in ManyChat step by step ... and opens nothing by itself; then do it with...'. The trailing API audit note is useful but phrased as an aside, and the ChatGPT/Claude/AI-agent framing in the first sentence adds little.

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 definition covers what it returns (screens, buttons, fields) and what it does not do. The remaining gap is how the agent identifies which conversation to act on once in the browser, which is left implicit.

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 description implicitly confirms no targeting input is needed by explaining the agent navigates the Cloud Browser itself.

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?

Names a specific verb and resource (read inbox conversation) and, crucially, discloses that the tool actually returns step-by-step ManyChat instructions rather than conversation content. That distinguishes it from a plain read, though it does not contrast itself with the adjacent cotlet_app_guide or cotlet_browser_read siblings.

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?

The description states the workflow clearly: get the steps here first, then execute them with cotlet_browser_* tools in the ManyChat Cloud Browser, and notes it opens nothing by itself. It also flags the official-API constraint (Pro plan or higher, narrow scope), which informs when this is the viable route. It lacks an explicit 'do not use this when...' exclusion.

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