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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and openWorldHint=false, so the description's main job is to explain why a tool named "publish" is read-only — which it does explicitly ("opens nothing by itself"). The additional disclosure that the response is a step-by-step screen/button/field guide, plus the dated note that self-provisioned Toast API access is read-only, is real behavioral context not present in the structured fields. Return-shape detail is somewhat thin, but no output schema exists to compensate.

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 content — that this returns instructions and the browser tools execute them — appears early and is unambiguous. However, "from ChatGPT, Claude or any AI agent" is filler, and leading with "Publish shifts" before the clarification risks a misread in the first clause. The Toast API caveat is relevant but appended as a trailing aside rather than integrated.

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 what the agent most needs: what comes back (step-by-step screens, buttons, fields), that nothing is mutated, and which tools finish the job. The API limitation explains why this indirect route exists. Only the relationship to the sibling toast_create_shift is left unaddressed.

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 there is nothing for the description to disambiguate and the baseline applies. The description does not add parameter meaning, but none is needed for an argument-free tool.

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 states the resource (shifts in Toast) and then clarifies the crucial nuance that the tool returns step-by-step instructions rather than performing the publish itself: "Returns how to do it in Toast step by step (screens, buttons, fields) and opens nothing by itself." That resolves what the verb actually means here. It does not, however, distinguish this from the sibling toast_create_shift, so the agent must infer the boundary between creating a shift and publishing one.

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 an explicit workflow: call this to get the steps, "then do it with the cotlet_browser_* tools in the user's Toast Cloud Browser," which names the alternative tools to use for the actual action. The API note implicitly explains why the direct-API route is not an option for writing. There is no explicit "do not use when..." exclusion, and no pointer to toast_create_shift as a different path.

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