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

Annotations already establish readOnly, idempotent, non-destructive, non-open-world semantics, so the burden is light. The description adds that this returns the full instruction text for the chosen skill (content, not state) and is 'on-demand,' which usefully tells the agent this is a pure lookup that yields guidance.

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, zero waste, purpose and trigger conditions front-loaded before the return-value note. Nothing redundant.

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 single-enum, read-only lookup with no output schema, the description covers purpose, timing, and what comes back ('the full instructions'). Nothing an agent needs to invoke it correctly is missing.

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 100% with a single enum parameter, so the schema already documents the argument. The description's parenthetical examples map real agent intents (adding animations, building forms) onto the enum values, adding marginal selection value beyond 'Which skill's guidance to load.'

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 and resource ('load ... guidance for a specific area') and names concrete triggering tasks (animations, page composition, copywriting, forms, nav, symbols). It is clearly distinguishable from swebsy_list_skills (which enumerates rather than loads one), though it doesn't name that sibling 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?

Gives clear usage context and timing: 'before acting on it,' with six concrete examples of the actions that should precede a load. No explicit when-not or named alternative is offered, so it stops short of a 5.

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