get_preferences

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

With no annotations and no output schema, the description carries the burden, and it does disclose two useful behaviors: the set of fields returned and the 'configured is false → run SETUP' branch. It does not state whether the read is side-effect free, what 'configured' actually means or where it comes from, or how an unconfigured user's response differs beyond the SETUP prompt.

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?

Two sentences with no filler, but the first is telegraphic — a comma-spliced noun phrase with a nested parenthetical — and lacks a subject or verb, which makes it ambiguous whether those fields are inputs or outputs. The actionable SETUP instruction is correctly placed second, but the opening is harder to parse than its length warrants.

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 simple one-parameter getter with no annotations and no output schema, the description does cover the returned fields and the setup follow-up, which is most of what an agent needs. It still leaves user_id handling, the meaning of 'configured', and the shape of the returned object unexplained, so it is adequate but not complete.

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 single parameter user_id is never mentioned in the description, including its 'default' fallback behavior or whose preferences are returned when omitted. With the schema providing no descriptions, the description needed to compensate and does not. The only usable signal is the implicit single-user scope of the tool.

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 is a bare noun list of preference fields ('Topics…, question types, goal, timezone, data location') with no verb, so the agent must infer that this tool retrieves current preferences. It is distinguishable from set_preferences only by the tool name, not by any statement in the description. The field list hints at content but never states 'returns the user's current preference values'.

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?

One concrete conditional is given: 'If configured is false, run SETUP: ask which topics (any, several allowed) and level' — that is a real selection rule and includes a helpful clarification on multi-topic selection. However, there is no guidance on when to prefer the sibling setters (set_preferences, set_settings) over this read, and no stated precondition for the normal path.

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