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

Annotations already declare readOnlyHint and destructiveHint=false, and the description adds meaningful behavior beyond them: the tool performs no action itself, returns screen/button/field-level instructions, and requires a separate browser tool call to act. The note about Zammad having a REST API but no official MCP server is tangential trivia rather than useful behavioral disclosure.

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 central fact — this returns instructions and opens nothing — is buried mid-sentence inside a long compound sentence, and phrases like "from ChatGPT, Claude or any AI agent" and the dated API note add bulk without helping selection or invocation. Reordering so the no-side-effect nature leads would make it materially easier to parse.

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 guide tool, the definition covers what the tool is and the two-step workflow, but leaves open whether the returned steps are generic or tailored to the user's account, and gives no sense of the returned content's shape or length. Adequate but with visible gaps.

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 has zero parameters and full schema coverage, so the baseline is 4. The description's explanation that it returns generic step-by-step guidance (rather than executing a query) implicitly accounts for why no search/filter arguments exist, though it never explicitly says the search criteria are conveyed in natural language to the agent.

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 a specific verb and resource ("Search tickets in the user's own Zammad account") and then clarifies the actual mechanic: it "Returns how to do it in Zammad step by step" and "opens nothing by itself." That distinction is essential and is stated, but it arrives after a phrase that suggests a real search operation, so an agent must read the whole first sentence to learn the tool only produces instructions.

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 follow-up path: after getting the steps, "do it with the cotlet_browser_* tools in the user's Zammad Cloud Browser," which tells the agent how this tool fits into a sequence rather than being an end in itself. It does not state explicit exclusions (e.g., when to prefer cotlet_app_guide or the mutating zammad_* siblings), so guidance is clear but not exhaustive.

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