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

Annotations already declare readOnly/idempotent/non-destructive, so credit here goes to the extra disclosure: the returned artifact set (details, source, latest version, SKILL.md text as a signed-in reader sees it, canonical URL) and the explicit 'does not install or run' boundary. It doesn't cover not-found behavior or what 'signed-in reader' visibility implies for anonymous callers.

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?

One front-loaded sentence with no waste; the read-only scope statement is appended as a short clause rather than a redundant paragraph.

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?

An output schema exists, so return values need only be summarized, and the description does that. For a single-param read tool with full annotations, the only real gap is error/missing-slug behavior, which is minor.

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% and the slug's pattern, length bounds, and source ('from search_skills') are already documented in the schema. The description adds only the implicit constraint that the skill must be public, so baseline 3 is correct.

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?

Specific verb + resource + scope: 'Read one public Skills Hub skill' plus the exact payload (details, source, latest version, SKILL.md text, canonical URL). This clearly separates it from siblings like search_skills, generate_skill, and get_prompt.

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 rules out mutation ('Read only; it does not install or run the skill'), which is useful exclusion guidance. However, it never states when to pick this over search_skills or generate_skill — the pointer to search_skills appears only in the parameter schema, not the description itself.

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