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

Annotations only declare readOnlyHint/idempotent/non-destructive, which an agent could misread as 'does the write safely'. The description adds the crucial fact that it 'opens nothing by itself' and only returns procedural steps, which is real behavioral context beyond the annotations and is consistent with them. What it omits is whether the caller must have the Zendesk Cloud Browser session already open and what form the returned steps take.

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 load-bearing content is two sentences, but a third sentence is appended about Zendesk's official REST API and the absence of a Zendesk-hosted MCP server (with a checked date). That is contextual filler that does not help an agent select or call the tool and dilutes the front-loaded signal. The opening sentence is also long and self-qualifying rather than direct.

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 guidance tool with no output schema, the description covers the essentials: what is returned (step-by-step screens, buttons, fields) and what to do next with the browser tools. It leaves open prerequisites (must the app be connected, must a browser session exist) and whether the returned steps are prose or structured, which matters for an agent planning the follow-up call.

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 the baseline is 4 and there is no parameter semantics to add beyond the schema. The description does not need to explain inputs and correctly does not attempt to.

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 makes the specific resource (Zendesk internal note) and the actual deliverable clear: it 'Returns how to do it in Zendesk step by step (screens, buttons, fields)'. That is a vital correction to a name that reads like a write action, and it lets an agent know this is a guidance tool, not an executor. It falls short of 5 because the first clause ('Add internal note in the user's own Zendesk account') superficially restates the title before the real behavior is revealed, forcing the reader to reconcile the two.

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 gives a forward path — 'then do it with the cotlet_browser_* tools in the user's Zendesk Cloud Browser' — which is genuine usage guidance for the follow-up step. However, it never says when to pick this over sibling Zendesk tools such as zendesk_update_ticket, zendesk_reply_to_ticket, or cotlet_app_guide, and gives no prerequisites or exclusions.

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