set_preferences

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

With no annotations provided, the description carries the full burden and does so excellently. It discloses that the layer is fully replaced, that '{}' clears it, how project_id scoping works, and that login is required. This goes well beyond typical descriptions.

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 dense but well-structured, front-loading the core purpose. Every sentence adds essential information. Slight redundancy (e.g., 'STANDING' and 'DURABLE') and an arguably long example keep it from being perfectly concise.

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 (nested object, two params, no annotations, no output schema), this description covers all necessary aspects: purpose, usage, parameter semantics, behavioral nuances, and even an agent instruction to record the preference. No critical gap is apparent.

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 the description fully compensates. It explains the 'facets' shape with a concrete JSON example, clarifies the full-replace semantics, and details the project_id behavior, including the null/omitted default. This is exemplary parameter documentation.

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: storing the caller's STANDING facet layer so it applies to every future 'recommend' call without being re-sent. It uses a specific verb ('Store') and resource ('facet layer'), and distinguishes this from per-call facets, making its scope unambiguous.

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 explicitly explains when to use this tool ('the right home for a DURABLE preference/constraint') versus the alternative of per-call 'facets' for task-specific needs. It also mentions the login requirement and advises noting the preference in memory, providing clear operational guidance.

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