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

Beyond the readOnly/idempotent annotations, it discloses the key trait an agent needs: it opens nothing by itself and returns UI-level instructions (screens, buttons, fields) that must be carried out elsewhere. That is real value not present in the annotations. It doesn't say what the instruction payload looks like in failure cases or whether it depends on account/app state.

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 is front-loaded and efficient, but the trailing sentence about Humanitix's API version and the absence of an official MCP server (with an odd future-dated 'checked' stamp) is filler that does not help the agent invoke this tool. It could be cut without loss.

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?

With no output schema, the description carries the return-value burden and does so: step-by-step screens, buttons, and fields, no side effects. Combined with the routing to browser tools, an agent has enough to call and chain it correctly; only edge-case behavior is unstated.

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 no parameters, so there is nothing for the description to clarify beyond confirming it is argument-free; the baseline of 4 applies. No misleading parameter claims are made.

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+resource (resend order confirmation in Humanitix) and immediately clarifies the actual behavior: it returns step-by-step instructions rather than performing the resend. That correction is essential for an agent, though the header phrasing still reads like an action tool until the second clause.

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?

Explicitly routes the agent: use this to learn the steps, then execute with cotlet_browser_* in the user's Humanitix Cloud Browser. This distinguishes it from the browser siblings and from sibling humanitix_* write tools. It does not state exclusions or prerequisites (e.g., ordering/refund states where resend is unavailable).

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