Install Skill

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

Beyond readOnlyHint=false, the description discloses the concrete guardrail: it refuses and names the offending files when local edits are detected, with overwrite as the explicit bypass. It also states 'Never runs anything,' which is important safety context the annotations alone cannot convey for an installer.

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 short sentences: what it does and where, then the refusal condition, then the safety guarantee. Zero filler and the most decision-relevant fact (destination) is front-loaded.

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 4-parameter write tool with no output schema, the description covers destination, refusal behavior, and side-effect safety, which is most of what an agent needs. Minor gaps remain: it doesn't say whether the destination directory is created if absent, or what the tool reports on success (e.g., the list of installed files).

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 baseline is 3. The description still adds meaning by pinning down the default target path and by tying overwrite to the edited-since-install refusal, which clarifies the interaction between two parameters rather than merely restating them.

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 gives a specific verb (Install), a specific resource (a skill published to SystemDox), and the destination (this computer, defaulting to ~/.claude/skills/<name>/). The phrase 'published to SystemDox' implicitly frames it as the counterpart to publish_skill and distinct from list_skills, so an agent can route correctly without opening a schema.

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 states the default install location and the exact condition under which installation is refused (a file edited since install), plus the escape hatch (overwrite true). That is strong conditional guidance, though it doesn't explicitly name sibling alternatives or address when to prefer a repo-local target over the global default.

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