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

Goes well beyond the annotations: discloses that without confirm:true the call is a dry run that changes nothing and reports what would change, while disabling takes effect immediately. Also surfaces the organizational policy failure mode and names lmcp_state as the way to inspect current state.

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-loads what the tool does, then the call condition, then the confirm mechanics. Dense but nearly every sentence carries a distinct behavioral fact; the parenthetical action list in the first sentence is the only slightly redundant part.

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 still tells the agent what the response conveys (what would change when confirm is missing) and how to check current state via lmcp_state. Nothing an agent needs to invoke it safely is missing.

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 baseline is 3; the description still adds meaning by explaining the intent behind each allowed value and the gating role of confirm. The action parameter is handled only by prose summary rather than added detail beyond the enum's own description.

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 (turn on/off) and a specific resource concept ('allowed without asking' for one kind of action), plus concrete action examples (emails, deletes, terminal commands). An agent can distinguish this from siblings because it also points at lmcp_state as the read counterpart.

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?

Explicit trigger condition ('Call it only when the person asked for it in this conversation'), mapping of allowed:true to 'don't ask me again' and allowed:false to wanting to be asked again, plus a hard prerequisite (confirm:true) and an exclusion (IT policy may forbid enabling). Little is left to inference.

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