manage_preferences

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

The annotation readOnlyHint=false is consistent with the description's "Read or update" framing, so no contradiction. The description adds the useful behavioral note about calling "get" at conversation start, but it does not disclose side effects of "set", "add_favorite", or "remove_favorite" such as overwriting preferences or permanently deleting favorites. These details are partly in the schema but not in the description.

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 two concise sentences, front-loaded with the main purpose and a clear usage instruction. Every word contributes value; no redundancy or filler.

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?

The tool has 4 actions and 8 parameters, but the description does not mention the add_favorite or remove_favorite actions explicitly, nor does it describe the output shape of a "get" call. The schema fills in parameter details, but the description alone is only minimally complete for a multi-action preference tool.

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 description coverage is 100%, so each parameter is already documented with action-specific semantics. The description only enumerates preference categories (style, aspect ratio, model, etc.) and does not add new meaning beyond the schema. This meets the baseline for full schema coverage.

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 reads or updates user preferences and lists the specific preference fields (default style, aspect ratio, model, style notes, favorite prompts). This specific verb+resource combination differentiates it from the sibling tools, which are mostly generation or asset tasks.

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?

The description gives explicit usage context: call with action "get" at conversation start to load preferences. It does not explicitly mention when not to use the tool or alternatives, but the context is clear and sufficient given the tool's unique role among siblings.

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