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

Annotations already flag destructiveHint=true and idempotentHint=true, so the bar is lower, yet the description adds genuine behavioral context: partial-patch semantics, that the bot answers only from published pages and public collections, that leads land in Form Submissions as 'Chat', and that visibility depends on an AgentFloatingBubble/AgentChat node plus available AI credits. It stops short of explaining auth requirements or what happens when credits run out mid-session.

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?

Two sentences, purpose front-loaded before the visibility/credit caveats. The second sentence is dense but each clause (data sources, lead destination, render conditions, credit gate) carries distinct information rather than padding.

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 no output schema and annotations covering the safety profile, the description does most of the needed work: it explains side effects, render preconditions, and the patch model. Remaining gaps are the return shape and permission requirements, which are minor for an idempotent settings updater.

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, but the description adds a parameter-level fact the schema does not encode: that this is a merge/patch operation where omitted fields are left untouched. That distinction between omitting a field and passing an empty value is exactly the kind of semantic the schema only partially implies.

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?

States a specific verb and resource ('Change the site's chat bot settings') and immediately pins down the mutation model with 'only the fields you pass change'. An agent can distinguish this from the read-side sibling get_site_chat without opening either 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?

The description implies usage context (chat settings for a site, gated on published pages/collections and owner AI credits) but never says when to reach for this tool versus get_site_chat, nor states prerequisites as instructions. It is usable guidance by inference rather than explicit routing.

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