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

Beyond the annotations, the description discloses the concrete state change (the org-level selection is deleted and the lane falls back to its default tier) and the authorisation requirement, which the annotations do not cover. It doesn't address idempotency of repeated clears or what error surfaces for an invalid lane, leaving a small gap against the idempotentHint=false declaration.

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?

Front-loaded with the verb and effect, then prerequisites, then permissions — a sensible ordering with no filler. The parenthetical CLI-twin reference is the only element that could be trimmed, though it usefully disambiguates for CLI-familiar agents.

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 one-parameter mutation with no output schema, the description covers effect, valid input source, and permissions — enough to call it correctly. It stops short of saying what a successful response looks like or how failures behave, but with no output schema that omission is minor.

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 single parameter already documents itself as 'The lane, as get_ai_settings lists it.' The description restates the same constraint rather than adding format, casing, or enumeration details, so the schema is doing the heavy lifting — baseline 3 applies.

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 names a specific verb+resource ('Return one AI lane to its default model') and immediately states the exact effect: the organisation's selection for the lane is removed. It also anchors itself against siblings by naming the CLI twin and by pointing to get_ai_settings as the source of valid lanes, making it distinguishable from set_ai_lane_model and list_ai_models.

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 a clear usage condition (lane must be one of the lanes get_ai_settings lists) and states the permission gate (ai.manage, owners/admins). What's missing is an explicit counterfactual — e.g. 'use set_ai_lane_model to pin a specific model instead of reverting' — so the agent must infer the alternative rather than being routed to it.

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