unregister

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

With no annotations, the description carries the full burden and delivers: messages are retained but never shown again, keptMessages reports the count, the calling session is unregistered until re-register, bound tokens stop working, and other sessions acting as the removed agent are also unregistered. It also discloses the key-refusal rule for self-registering tokens and the MESSAGE_CP_AGENT re-registration side effect.

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?

Purpose is front-loaded and nearly every clause carries real information, but the body is one unbroken run-on paragraph with nested parentheticals that make the conditional modes hard to parse. Content earns its place; structure does not help the reader.

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 mutation tool with no annotations and no output schema, the description covers side effects, auth/token rules, message retention, and re-registration behavior. An agent has everything needed to invoke it correctly and anticipate consequences.

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 baseline is 3, but the description adds genuine semantics beyond the schema: omitting name removes the caller, key is required only if the agent has one, and key is outright refused for tokens approved to register their own agents. This goes beyond the terse schema descriptions.

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?

Opens with a specific verb+resource: "Remove an agent from the directory and free its name." This is immediately distinguishable from siblings like register, list_agents, and get_agent, and the scope (directory entry + name release) is explicit.

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?

Enumerates invocation modes conditionally: no arguments removes yourself, name+key removes another agent with key match, token-bound sessions have restricted behavior. This effectively tells the agent which parameter combination applies in which context. It stops short of explicitly contrasting with sibling tools (though register is named as the recovery path), keeping it just under a 5.

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