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

Beyond the simple annotations, the description discloses key behavioral details: importing only stores the skill, state-changing steps are previewed and confirmed on later runs, name collisions are handled via non-colliding names, and the return value is {name, imported}. This significantly enriches the agent's understanding of side effects and safety.

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 compact and front-loaded, with three sentences each carrying essential information: the purpose, the safety model, and collision handling. There is no redundant or vague wording.

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 simple inputs and no output schema, the description is complete: it covers the source of inputs, the installation effect, the security behavior, collision resolution, and the return shape. The agent has enough context to invoke the tool correctly and set expectations.

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?

The input schema already provides 100% description coverage for both parameters, including the alias relationship between skill and skill_token. The description adds little beyond what the schema states, merely reiterating that a token or raw JSON can be passed. This is adequate but does not exceed the schema's clarity.

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 clearly states the tool's function: 'Installs a SKILL someone shared with you' and explains it does so by accepting a skill_token from recipe_export or a raw manifest JSON. It distinguishes the tool from siblings like recipe_export and recipe_run by explaining the import/use relationship.

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?

The description provides clear usage context: use this when someone shares a skill with you, and it mentions the exact input source (recipe_export token or manifest). However, it does not explicitly name alternatives or list exclusions, so an agent might not immediately know when to prefer recipe_import over the sibling recipe_install.

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