agent_stop

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

With no annotations, the description carries the full burden and does so well: it discloses destructive terminal semantics, exactly what gets destroyed in each state (workspace vs durable logical metadata), and explicitly bounds the blast radius (never stops the shared session or other agents). This is rich behavioral context beyond anything structured fields provide.

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?

A single dense sentence that front-loads the destructive semantics and the state-dependent outcome, then appends the scope bound. Every clause earns its place with no redundancy.

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?

Complete enough for a one-param destructive tool: it covers what is destroyed, in which states, and the blast-radius limits. Missing only an explicit return/error behavior, which is minor given no output schema exists.

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% and the schema fully documents agentId with a pattern and provenance note (returned by agent_start), so the baseline is 3. The description reinforces the agent-scoped nature but adds no new syntax or format detail beyond the schema.

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 (Stop) and resource (MCP-managed agent), and immediately distinguishes scope from siblings by clarifying it stops one agent, not the shared session or other agents. An agent can differentiate this from agent_suspend or process_kill from the description alone.

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?

Explains the semantic distinction between stopping an active agent (closes workspace) and a suspended one (discards metadata), which implicitly guides when to use this versus agent_suspend. It does not explicitly name agent_suspend as an alternative or state when not to use it, so it falls short of a 5.

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