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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds genuinely useful context beyond that: the tool performs no action itself ('opens nothing by itself'), returns procedural steps with screens/buttons/fields, and hands execution to the cotlet_browser_* tools. It does not describe output shape or how to recover if the steps do not match the live UI.

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 value — 'returns steps, does not act, continue with cotlet_browser_*' — is stated early and is tight. It is diluted by marketing filler ('from ChatGPT, Claude or any AI agent') and by a final sentence about Gorgias's REST API and MCP beta dates that adds no decision value and may mislead an agent into thinking this tool is an API client.

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 description covers what it returns, that it is side-effect free, and which tool family executes the mutation. That is enough to call it correctly. It stops short of saying whether the returned steps are specific to the ticket in context or generic, which would matter for an agent assembling a full update flow.

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 input schema has zero parameters and full coverage, so the baseline for a no-param tool is 4. The description correctly implies no inputs are required and instead frames the ticket target as something resolved inside the returned procedure and the browser session.

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 the resource (a Gorgias ticket) and the action, and crucially discloses that the tool does not actually perform the update: it 'Returns how to do it in Gorgias step by step (screens, buttons, fields) and opens nothing by itself.' That resolves the tension with the verb 'update' in the name. It does not, however, distinguish itself from siblings such as gorgias_apply_macro, gorgias_reply_to_ticket, or the cotlet_app_guide route, so an agent must infer the boundary.

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?

There is a clear downstream instruction — 'then do it with the cotlet_browser_* tools in the user's Gorgias Cloud Browser' — which tells the agent the follow-on step. But there is no guidance on when to pick this over the other Gorgias mutation siblings, no prerequisites, and no exclusions. The trailing note that Gorgias has a REST API and a hosted MCP server in open beta is informational and arguably invites confusion about which path to take rather than guiding selection.

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