laya_advisor_preferences

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

No annotations exist, so the description carries the full burden and largely meets it: it states that these settings 'authorize recommendations, not actual switching or any other action', that missing ceilings require setup with no automatic acceptance, that omitted squad preserves prior state, and that unconfigured values default to asking. It stops short of describing permission/auth requirements or write side effects on the host.

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 purpose sentence is front-loaded, which is good, but the remainder is a dense run of telegrams ('always: ask on every assessment; conditional: ...') without structural separation, making the policy modes and ceiling rules harder to scan than they need to be. Every sentence carries information, so little is wasted, but the packaging is weak.

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 present, return values need no explanation. Given zero annotations, the description supplies the behavioral context needed: defaults, the recommendations-only scope, and setup prerequisites. It is close to complete, with only auth/permission framing missing.

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 0% and every parameter is an untyped anyOf with no field descriptions, so the description must compensate fully. It defines policy's three values (always/conditional/auto), the ceiling shape {model, reasoning_effort}, the squad shape {enabled, reviewer:{model, reasoning_effort} or null} including null-reviewer fallback, and the models catalog's role.

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 opening states a clear verb+resource split: read preferences, or save only after the user's Confirm and continue. That is specific enough to distinguish read vs. write behavior. It does not, however, differentiate itself from the sibling laya_tell_me, leaving that boundary implicit.

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?

Explicit operational guidance is present: 'Omit policy to read', auto requires ceiling plus a verified models catalog, and unknown/unconfigured preferences default to asking. It explains within-tool conditions well but never names an alternative tool or when to reach for laya_tell_me instead.

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