get_website_embed_code

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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint, so the safety profile is covered; the description adds genuinely useful behavior context — that the output is a complete, paste-ready snippet with real IDs/region substituted, and that it should not be short-circuited by pointing the user at the dashboard. It does not mention any rate limits or failure modes, but with annotations present that is a minor gap.

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 imperative 'MUST CALL' lead is front-loaded and the trigger enumeration ('widget script, iframe code, popup chat bubble, or where is the code') mirrors real user phrasing, so it earns its words. It runs slightly long with overlapping trigger phrases, but nothing is filler.

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 read-only code-generation tool with full schema coverage and no output schema, the description covers purpose, triggers, exclusions, prerequisite lookup, and the shape of the returned snippet. An agent has everything needed to call it correctly without opening anything else.

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 coverage is 100%, so the enum and container params are already documented, but the description adds meaning the schema does not: the returned snippet comes with the real agent ID and region already filled in, and it tells the agent how to obtain agentId when unknown via list_agents. It stops short of explaining mode-specific behavior or how containerWidth/Height interact beyond the schema's 'full-width only' note.

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 a specific verb and resource (return a ready-to-paste HTML embed snippet) and enumerates the concrete artifacts produced (widget script, iframe, popup bubble, React voice example). It is clearly distinguishable from nearby siblings such as get_widget_css_styling_guide, which handles styling rather than embed code.

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 explicit trigger conditions ('MUST CALL whenever the user asks to deploy/embed/add their agent to a website... where is the code'), an explicit exclusion ('Do NOT redirect the user to the dashboard Channels/Deployment tab'), and a prerequisite path ('If agentId is unknown, call list_agents first'). This is exactly the when/when-not/alternative structure the dimension rewards.

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