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

With empty annotations, the description carries the full burden, and it discloses a crucial non-obvious behavior: the tool does not write the file itself — 'YOU must then create that file verbatim.' It also reveals the side effect 'Counts the install' and specifies exact installation paths per target, which is more than most definitions provide.

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 dense but not bloated; every sentence contributes critical information. The core purpose is front-loaded, followed by the return contract and parameter routing. It is longer than average, but the complexity of the tool (multiple targets, follow-up write action) justifies the length.

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?

There is no output schema, so the description correctly explains return values (complete skill file and path) and the required post-call action. It covers all parameter scenarios and paths. Minor omissions like overwrite behavior, error cases, and more detail on 'Counts the install' prevent a 5.

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%, so the baseline is 3. The description adds value by prescribing parameter choices for real-world scenarios: target=hermes, target=generic, scope=user for all projects, and agent= for hosted agents. This goes beyond the schema's field descriptions and helps the agent choose correct values.

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 a specific verb and resource: 'Install a skill into the agent you are running in.' It goes on to describe the return contract (complete skill file and exact path) and the agent's required follow-up, which clearly distinguishes this from sibling tools like get_skill, search_skills, and submit_skill.

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 explicit selection guidance for target ('Use target=hermes for Hermes Agent, target=generic for any other agent'), scope ('scope=user to install for all Claude Code projects'), and agent ('pass agent= to install there instead'). It does not explicitly contrast with alternative tools, but the parameter routing rules are concrete and actionable.

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