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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, and the description is consistent with them by stating it opens nothing by itself. It adds real behavioral value beyond annotations by specifying what is returned (step-by-step screens/buttons/fields) and what the agent is expected to do next. The closing sentence about Gorgias's REST API and MCP beta is irrelevant filler rather than behavior 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 core is front-loaded and efficient: what it returns, that it has no side effects, and the next step. But 'from ChatGPT, Claude or any AI agent' is padding, and the trailing sentence about Gorgias's official REST API and open-beta MCP server earns no place in an invocation description.

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 zero parameters and no output schema, the description covers the essentials: return shape is described as step-by-step guidance and the follow-up browser workflow is named. It is silent on a key practical point — how the specific macro is identified when the tool accepts no arguments — leaving an agent to guess how to scope the request.

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 with 100% schema coverage, so there is no parameter meaning for the description to add. Baseline for a no-parameter tool applies.

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 clear that despite the name 'apply_macro', the tool performs no mutation: it returns step-by-step Gorgias instructions (screens, buttons, fields) and 'opens nothing by itself'. That is a specific and usable statement of purpose, and the follow-up browser-tool workflow distinguishes it from a true executor. It does not explicitly contrast with siblings like gorgias_edit_macro, so it stops short of 5.

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?

Usage is implied through the sequence 'get instructions here, then act with cotlet_browser_* tools', which is useful routing context. However, there is no statement of when to choose this over gorgias_edit_macro or other ticket tools, and no preconditions (e.g., which macro, whether a browser session must be open) are given.

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