preferences

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

Annotations declare readOnlyHint=false and destructiveHint=false, so the agent knows the tool can mutate but is not flagged destructive; the description is consistent with this. The description adds useful context by disclosing the three modes of operation and the dotted addressing scheme, but says nothing about persistence, what a 'set' overwrites, or default behavior beyond what the schema's backend description already covers.

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?

Front-loaded with the verb, then a compact parenthetical enumeration of the three modes, followed by a single routing sentence. Both sentences earn their place, though the dense parentheticals make it slightly terse.

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?

With 8 parameters, no output schema, and moderate schema coverage, the description covers the addressing modes but does not describe what a 'get' returns or how values are interpreted on 'set'. It routes to list_preferences for names but leaves the return/behavior contract underspecified.

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 63%, a moderate baseline. The description clarifies how section and option combine (dotted nesting) and maps tool=<id> and document=true to their respective parameters, adding some meaning. However, the schema already documents tool, option, sprite, backend, and document, so the description largely restates the addressing modes rather than filling the uncovered params (section, value).

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 verb pair (gets or sets) and resource (Aseprite preference), and explicitly enumerates three addressing modes: app preference via app.preferences.<section>.<option>, tool preference via tool=<id>, and per-sprite document preference via document=true. It names the sibling list_preferences as the discovery counterpart, aiding differentiation, though it doesn't contrast against other siblings.

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?

Provides a clear routing instruction: 'Use list_preferences to discover names,' which points the agent to the alternative for enumeration. Usage is implied by the get/set duality, but no explicit when-not or prerequisites are stated.

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