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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, and closed-world, so the description doesn't need to carry the safety profile. It still adds real value by stating the return is a ready-to-paste HTML snippet with the real agent ID and region substituted in, and that voice-react yields a React example. It doesn't disclose whether the snippet is region-aware beyond a mention, or any quota/pagination behavior, keeping it below a 5.

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?

Front-loaded with the trigger condition, then the return value, then the anti-pattern, then the prerequisite — in descending order of decision value. Four sentences, no filler, no restatement of the tool name.

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?

There is no output schema, so the description must say what comes back — and it does (ready-to-paste HTML snippet with real agent ID/region, in one of four modes). Combined with annotation-covered safety and 100% schema coverage on the four parameters, an agent has everything needed to call this correctly on the first try.

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?

Schema description coverage is 100%, so the baseline is 3. The description adds meaning on top by hinting at the output modes ('popup, full-width inline, modal, or React voice-only example') and, more importantly, by telling the agent how to obtain an unknown agentId via list_agents. It doesn't explain containerWidth/containerHeight, which is left entirely to the schema.

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?

Starts with a specific verb+resource ('get_website_embed_code' semantics spelled out as deploy/embed code for a website) and enumerates the concrete artifacts returned: widget script, iframe code, popup chat bubble, or 'where is the code'. An agent can distinguish this from get_widget_css_styling_guide or create_channel_connect_link without opening any schema.

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?

Gives explicit triggers ('whenever the user asks to deploy/embed/add their agent to a website'), an explicit anti-pattern ('Do NOT redirect the user to the dashboard Channels/Deployment tab instead of returning this code'), and a prerequisite chain ('If agentId is unknown, call list_agents first'). This is the when/when-not/alternatives triad done properly.

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