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

Annotations only say this is not read-only, not idempotent, and not destructive. The description adds real behavioral context beyond them: the change reroutes every member's work on that lane to a different provider and changes who pays for it, and the caller must hold ai.manage as an owner or admin. That org-wide blast radius and auth requirement are exactly what an agent needs before mutating.

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 core action and its scope are front-loaded in the first clause, and the remaining sentences each carry distinct information (valid lane source, valid key source, blast radius, permission). It is a single dense sentence chain with mild repetition of the schema's parameter wording, but little genuine waste.

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 two-parameter mutation with an output schema absent and annotations only covering safety flags, the description covers the action, valid inputs, permission gate, and organizational impact. It does not say whether the change takes effect immediately or how to revert it via clear_ai_lane_model, which is a minor remaining gap.

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%, so the baseline is 3, but the description adds meaning the schema lacks by spelling out example lane values (stack READMEs, code review, troubleshooting, deploy analysis, CI/CD generation) in a schema with no enums. The model_key explanation largely repeats the schema wording, which keeps this from a 5.

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 and resource: 'Choose the model one AI lane runs on', plus the CLI twin `ankra ai lanes set`. It distinguishes the tool from related siblings by naming get_ai_settings as the lane source and list_ai_models as the model source, so an agent understands the exact scope without opening a schema.

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?

It gives concrete context for when and how to use the tool: the lane must come from get_ai_settings and the model_key from list_ai_models or an exact OpenRouter id, and it states the required ai.manage permission. It stops short of explicitly naming the counterpart clear_ai_lane_model as the way to unset a lane, so the when-not case is only implied.

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