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

Beyond the annotations (destructiveHint=true, idempotentHint=true, openWorldHint=true), it discloses real behavioral facts: changes take effect for every visitor instantly, plan-gated settings are rejected with the required plan surfaced, and writes are atomic ("nothing is written unless every value is valid"). The last point is especially valuable because it tells the agent a batch partial-failure will not occur.

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?

Roughly four sentences, front-loaded with the action, then preconditions, then side effects, then routing. Every sentence carries information, though the final sentence's "not the greeting or auto-trigger" clause is slightly tangled and could be trimmed.

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 two-parameter, non-read-only mutation with no output schema, the description covers side effects, atomicity, plan gating, and tool routing. The remaining gap is that it never says what a successful call returns (e.g., the updated settings or just a status), which leaves the agent guessing after invocation.

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 both parameters (and the nested setting object, including the widget_color example) are already documented in the schema. The description's "object of setting name to new value" adds no detail beyond the schema and does not enumerate valid setting names or value formats. Baseline 3 applies.

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?

"Change one or more chat widget settings" states a specific verb and resource, and the description immediately differentiates itself from get_widget_settings (read) and save_proactive_message (proactive messages). An agent can pick it out of a 46-tool sibling list without opening the 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 an explicit precondition workflow ("read them with get_widget_settings first") and an explicit exclusion with the correct alternative: autonomous/proactive messages go to save_proactive_message, "not the greeting or auto-trigger." Both when-to-use and when-not-to-use are stated.

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