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

Annotations already declare non-read-only, non-idempotent, non-destructive behavior; the description adds value beyond them by disclosing the required editor role, the prerequisite read to determine current state, and the fact that the response returns the new ai_on. The only gap is what happens on concurrent or repeated flips, but for a two-param toggle this is solid.

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?

Four short clauses, front-loaded with the toggle semantics before the prerequisite and the business rationale. Dense but every sentence contributes; the semicolon chaining is slightly compressed but not wasteful.

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, the description correctly compensates by stating the answer returns the new ai_on, and it covers auth (editor role) plus the read-before-flip workflow. For a simple two-parameter toggle this is nearly complete, missing only error or re-flip behavior.

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% and both parameters are documented as ids returned by sibling list tools, so the schema carries the semantic load. The description adds no field-level detail beyond implying which conversation is targeted, so the 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?

"FLIPS the bot in one dialog: on becomes off, off becomes on" names a specific verb (flip) and a scoped resource (the bot in a single conversation), and the phrase "in one dialog" implicitly separates it from workspace-wide settings tools. It stops short of explicitly naming a sibling such as dosai_update_bot_settings, so the per-conversation vs global distinction must be inferred.

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 a concrete prerequisite ("Read dosai_get_conversation first (field ai_on) so you flip in the right direction") and a real use case ("Switching off is how an owner takes a client over personally"). No explicit when-not or named alternative is given, which keeps it below a 5.

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