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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so safety is partly covered; the description adds the non-obvious trust boundary that reading never installs, executes, or authorizes the skill, plus that referenced text assets are bounded and allowlisted. It stops short of describing the default when revision is omitted or what the response shape looks like, but the output schema covers the latter.

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?

Two sentences, front-loaded with the locate-then-read workflow, and the second sentence handles the safety boundary and the private-skill alternative. Dense but every clause earns its place; only 'bounded allowlisted referenced text assets' is slightly compressed into jargon.

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?

Read-only, output schema present, and the description covers the workflow prerequisite, the trust boundary, and sibling routing. Remaining gaps are the default revision behavior and what the allowlisted referenced assets concretely are — useful but not blocking for a correct call.

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 0%, so the description carries the burden: it clarifies that path must be the exact skills/<name>/SKILL.md form (matching the regex) and that revision pins the corpus revision. However, it does not state the revision format (40-hex SHA) or what happens if revision is omitted, leaving real gaps for a two-parameter tool.

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?

States a specific verb and resource — read a shared skill's exact skills/<name>/SKILL.md — and names the sibling pair (private_skill_list / private_skill_get) that covers the other case. An agent can distinguish this from community_search and private_skill_get without opening any 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?

Gives an explicit prerequisite workflow (locate the path with community_search first, then read at that corpus revision) and an explicit exclusion (private user skills go to private_skill_list / private_skill_get). Nothing about when to choose this tool is left to inference.

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