configure_council

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

The annotations are minimal (readOnlyHint=false), so the description carries the behavioral disclosure burden and does so extensively. It discloses persistence across restarts/reloads, partial-update semantics, validation of judge_model (rejecting unparseable values), default behavior for auto_council, and reasoning_effort clamping across mixed councils. This is far beyond the annotations.

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, well-structured sentence that front-loads the primary purpose and then adds behavioral details. Every clause provides necessary context, and there is no redundant or filler content. It is appropriately concise for a tool with six parameters.

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 (6 parameters, no output schema, rich validation rules), the description is quite thorough. It covers the update semantics, persistence, partial updates, and subtle behaviors like judge_model auto and reasoning_effort clamping. It does not explicitly describe return values, but since there is no output schema, this is a minor gap; the core invocation context is well covered.

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?

The input schema already provides 100% coverage with detailed parameter descriptions, setting a baseline of 3. The description adds extra meaning by explaining that each field is persisted and that unset fields are untouched, which applies to all parameters. It also introduces cross-parameter semantics like auto_council interacting with models and reasoning_effort overriding, which the schema does not capture.

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 clearly states the tool's purpose: "Update the council configuration" and enumerates the specific editable aspects (models, judge, response mode, deconfliction rounds). It distinguishes itself from siblings like setup_council and get_council_config by using the verb "update" and by mentioning persistence relative to setup_council.

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 provides clear context for when to use this tool: it is an update operation on existing council configuration. It explicitly states that "a field left unset is untouched," which is valuable partial-update guidance. It does not explicitly rule out setup_council, but the sibling names and the phrase "same as setup_council's tier choices" give a clear sense of the intended use.

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