agent_configure

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

No annotations are provided, so the description carries the full burden. It discloses key behavior: no restart, context preserved, and uses CLI-standard /model//effort commands per agent type. However, it does not disclose failure modes, behavior when an invalid model is specified, or whether the change is reversible.

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 a single dense sentence that front-loads the core purpose (change model/effort without restart, preserve context) and then adds the mechanism per agent. It is efficient with no wasted words.

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 an output schema covering return values and schema covering parameters, the description is reasonably complete for a multi-agent configuration tool. It covers supported agents and mechanics but lacks explicit usage/selection guidance, which is a minor gap for a tool with many sibling interaction tools.

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 67%, and the description explicitly mentions model and reasoning effort, mapping to two of three parameters. It adds the agent-specific behavior context but does not add syntax/format details beyond the schema. session_id is not semantically expanded, though it is self-evident.

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 states a specific action — changing the model/reasoning effort of already-launched agent sessions (Claude/Codex/Grok/Composer) without restarting. It clearly distinguishes from sibling tools (pty_send, claude_turn) by focusing on reconfiguration rather than interaction.

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 implies when to use it (to modify running agent sessions while preserving context) and explains the per-agent mechanism, but it does not state explicit exclusions, prerequisites (e.g., session must be active/launched), or when NOT to use this tool versus alternatives like closing and reopening via pty_close/pty_open.

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