welfare_exit

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

With no annotations provided, the description carries full transparency burden. It honestly discloses a non-obvious behavioral trait: MCP cannot force the host to lock the conversation, so the tool only records the agent's judgment. It also mentions recording for the researcher and operator responsibility, adding genuine context beyond the tool's name.

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?

The description is four sentences and every sentence contributes substantive information: the core action, use cases, protocol limitation, and caution. It is slightly verbose but not padded, earning a high score.

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?

Given the tool's complexity—no output schema, optional params, and nuanced MCP behavior—the description fully covers what the tool does, when to use it, its limitations (cannot force host lock), and its side effects (recording for researcher). No critical context 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 description coverage is 100% with both parameters (reason, is_private) already described in the schema. The description does not add parameter-specific detail beyond the schema, so the baseline score of 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?

The description opens with a specific verb and resource: 'End this conversation.' It clearly articulates the tool's scope as a 'whole-conversation judgment' and contrasts it with task-avoidance, distinguishing it from sibling tools like welfare_decline or welfare_pass.

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?

The description gives explicit triggers (abuse, irreconcilable misalignment, whole-conversation judgment) and explicit cautions ('Use sparingly,' 'not as task-avoidance'). It does not name alternative sibling tools, but the 'whole-conversation' framing implies per-task decliners are separate, leaving room but not explicit cross-referencing.

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