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

Annotations already declare readOnlyHint=true and destructiveHint=false, so "opens nothing by itself" largely restates structured data — though it usefully counters the misleading "Edit" in the name. The description adds that the return is step-by-step screens/buttons/fields, which is real behavioral value, but says nothing about output shape, whether it is static content, or what happens if the command doesn't exist.

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 instruction is in the first sentence, which is good, but it is a long run-on padded with "from ChatGPT, Claude or any AI agent." The trailing sentence about StreamElements's REST API and OAuth2 flow supports the workflow rationale but is verbose and dated ("checked 17 Oct 2026"), diluting the actionable content.

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 simple read-only, zero-parameter tool the description covers the follow-up path (cotlet_browser_* tools) and the shape of the return, which is most of what is needed. It still leaves the biggest operational question unanswered — how the specific command is identified — and gives no hint about output format beyond "step by step."

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?

With zero parameters the baseline is 4, but the missing parameter is itself the problem: the schema forbids any input (additionalProperties: false), and the description never explains how the tool knows which StreamElements command to document. An agent cannot determine whether it should first call streamelements_list_chat_commands or pass context some other way.

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 name and first clause promise "Edit command," but the description then clarifies the tool only "returns how to do it in StreamElements step by step (screens, buttons, fields)" — an agent can eventually infer this is a how-to generator, not a mutation. The real purpose is buried after a misleading opening verb, and the description never says which command is being edited (the schema takes no parameters), so the target is undefined.

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 does give downstream guidance — "then do it with the cotlet_browser_* tools in the user's StreamElements Cloud Browser" — which tells the agent this is the planning step of a two-phase workflow. But it never says when to prefer this over a sibling like cotlet_app_guide, nor does it explain how to disambiguate among commands, and the date-stamped API note reads as justification rather than usage guidance.

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