preferences

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

With no annotations, the description carries the full burden, and it does disclose a genuinely important behavioral trait: security-sensitive keys (WebUI port, password, host-header validation) are refused with no override. It does not cover auth requirements, whether writes persist or need a restart, or side effects, but the refusal disclosure is substantive non-obvious context.

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 tight sentences with the core action front-loaded and the safety constraint second. Nothing is wasted and the structure leads with what the tool does.

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?

An output schema exists, so return values needn't be explained, and all three params are documented in the schema. The description adds the critical refusal behavior, leaving only auth/persistence details as minor gaps.

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 the schema already documents keys, action, and values. The description only loosely echoes 'subset'/'read/write' without adding format or syntax detail beyond the schema, so the baseline 3 applies.

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?

States a specific dual-mode verb (read/write) on a specific resource (preferences) and clarifies that writes apply only to a subset. This clearly sets it apart from the torrent-management siblings, though it never names an alternative tool explicitly.

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?

Usage is implied by 'read preferences, or write a subset,' and the refusal rule hints at when writes will fail, but there is no explicit guidance on when to choose this tool over qbt_call or other siblings, nor any stated prerequisites.

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