Change a subagent's model

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

With no annotations provided, the description carries the full disclosure burden and exceeds it: it discloses the underlying call (session/set_config_option), the verification behavior (confirms the echoed value), the failure conditions (rejected while not idle), and input validation (checked against the advertised model list). This is exemplary coverage for a tool with zero annotation support.

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?

Three sentences, zero filler, with information front-loaded: action+mechanism+verification first, then failure conditions, then validation. Every sentence earns its place and no idea is repeated.

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 2-parameter config tool with no output schema and no annotations, the description covers purpose, preconditions, mechanism, verification, and validation — all core call decisions. The remaining gaps are minor: no explicit statement of the success/failure return shape beyond echoing the value, and no mention of whether the change persists or requires session restarts.

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% and both parameters are already well-documented ('Subagent handle returned by spawn' and 'Model id from the session's advertised list'), so the baseline is 3. The description adds only marginal value — the worked example 'swe-2-high' and the validation behavior — rather than clarifying parameter meaning 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?

The description states a specific verb-resource pair ('Switch an idle session's model') plus the implementation mechanism ('via session/set_config_option') and a concrete example echo value ('swe-2-high'). This clearly distinguishes it from siblings like set_mode (mode changes), models (listing), and the lifecycle tools (interrupt/stop/resume).

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 preconditions ('idle' session), explicit rejection states ('starting/running/stopped/dead'), and a concrete remedy ('resume or wait for idle first'). It stops short of naming sibling tools as alternatives — notably the models tool that would provide the advertised list — which is the only gap.

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