agent_run_skill

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

Beyond the annotations (readOnlyHint=false, destructiveHint=true), the description adds valuable details about execution mechanisms: Python skills run in-process, shell skills via subprocess, and markdown skills return file contents. It also discloses the return format and timeout behavior. It doesn't explicitly warn about side effects, but the destructive hint covers that, so the additional execution context earns a 4.

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 well-structured and concise: a clear opening, a brief explanation of skill types, an Args list, and a Returns section. Every sentence contributes useful information without unnecessary fluff, making it easy for an agent to parse.

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 5 parameters, an output schema, and annotations, the description covers all necessary aspects: it explains the skill execution model, the meaning of each parameter (already in schema), and the return JSON structure. It also accounts for edge cases like timeout with the 'timed_out' key. There is no obvious missing information that would hinder correct invocation.

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 all parameters. The description's Args section largely repeats the schema descriptions (e.g., 'Primary input passed to the skill as the first argument' matches the schema exactly). It adds no new semantic nuance beyond what the schema provides, so the baseline 3 is appropriate.

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 opens with 'Invoke a discovered skill by name and return its result', which is a specific verb+resource pair that clearly identifies the tool's function. It also differentiates from sibling tools by focusing on skills rather than commands, files, memory, or web search.

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 context on when to use the tool: when a skill is discovered. It explains the three skill types and their execution methods, which helps the agent understand what will happen. However, it does not explicitly state alternatives or exclusion criteria, such as 'For raw shell commands, use agent_execute_command', so it stops short of a full 5.

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