nexus_update_preferences

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

The description discloses the crucial partial-update behavior ('Only the provided fields are changed; omitted fields stay as-is') and the return format ('JSON {success} or an error string'). Annotations already declare non-destructive and idempotent, so the description builds on that without contradiction. It does not note authentication or error details, but the partial-update and return semantics add real value beyond annotations.

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 three sentences with no fluff: purpose, behavior, and return. It is front-loaded with the core action and provides the key behavioral nuance immediately. Every sentence earns its place.

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 tool with 26 optional parameters, the schema thoroughly documents each one. The description covers the overall behavior (partial update), points to the read tool for pre-fetching, and specifies the return format. No critical operational detail is missing for an agent to call this correctly.

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 every parameter has a descriptive comment in the schema. The description adds a generic semantic that applies to all parameters: only provided fields change, which is helpful but not per-parameter. Given the high schema coverage, the baseline of 3 is appropriate; the description does not enumerate or elaborate on individual parameters beyond the schema.

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 states a specific action: 'Update the current user's site preferences via v2 GraphQL.' The verb 'Update' plus the resource 'site preferences' clearly distinguishes it from siblings like nexus_update_about_me and nexus_update_country, and from the read-only nexus_get_preferences. The partial-update note adds further specificity.

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 mentions the read counterpart: 'Read current values with nexus_get_preferences,' which guides the agent to fetch existing preferences first. While it doesn't explicitly exclude other update tools, the resource name 'preferences' makes the appropriate context clear. This is sufficient guidance but lacks an explicit 'when not to use' statement.

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