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

Annotations only say destructive/idempotent/not-read-only. The description goes far beyond: messages off still delivers to the dashboard and lets scheduled follow-ups fire; comments off means comments are neither answered nor recorded and re-enabling does not backfill them; follow-ups are platform-scoped, not connection-scoped. This is exactly the side-effect detail an agent needs for a destructive toggle.

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 core purpose, then dense but purposeful paragraphs on each switch's behavior and the failure modes. Every sentence carries information, though the error-code parentheticals and platform note make it long for a four-parameter toggle.

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 only partial schema coverage, the description carries most of the burden and does so well: failure codes, side effects, and recovery caveats are all present. Minor omissions remain (e.g., whether omitted switches are left untouched, and what a successful response contains).

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 50%: both UUIDs are documented in the schema, but respond_to_comments and respond_to_messages have no schema descriptions. The description compensates by explaining what each switch governs and its downstream effects, though it never names the parameters directly, leaving the mapping to inference.

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+resource ('Switch the AI on or off for a connection') and enumerates the two axes affected (messages, comments). It implicitly scopes to a connection, which distinguishes it from the conversation-level sibling resume_conversation_ai, but it never names that alternative explicitly.

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 concrete operational conditions: at least one setting must be sent or 422 no_settings; a disconnected connection cannot be changed (409 connection_inactive); reconnecting resets both switches so they must be set again. It offers no explicit when-to-use guidance against sibling tools like resume_conversation_ai or update_follow_up_settings.

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