load_skill

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered; the description still adds value by clarifying the return contract (instructions for the task) and by ruling out side effects (no installing, no script execution). It doesn't mention size limits or errors for a missing path, which keeps it short of a 5.

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?

Three tight sentences with zero filler: purpose first, then the operating sequence, then the boundary condition. Nothing is buried, and every sentence carries distinct information.

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 only two well-documented parameters and no output schema, the description has to carry the return-value story, and it does: it says instructions come back plus a file list used for follow-up loads. It stops just short of describing what a skill file's contents look like or what happens when a path doesn't exist.

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 both parameters are already fully documented, including the SKILL.md default and the relative-path format. The description's mention of starting at SKILL.md and following the returned file list is workflow context rather than added parameter semantics, 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?

A specific verb ("read") plus a specific resource ("a public Vapi skill or one of its supporting files") tells the agent exactly what the tool does. The closing clause ("does not install skills or execute scripts") separates it from anything that would mutate state or run code, and the two-parameter shape makes it easy to tell apart from siblings like search_skills.

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 gives real sequencing guidance: start with SKILL.md, then load relevant files from the returned file list as needed. What's missing is any pointer to search_skills for discovering the exact name (that hint lives only in the schema) and any explicit statement of when not to use it.

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