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

Annotations already declare read-only, idempotent, closed-world behavior, and the description adds real value on top: expected_hash acts as an optimistic-concurrency guard that refuses changed instructions, and the prompt-injection warning tells the agent how to treat returned content. It does not state what error surfaces on hash mismatch, which keeps it short of a 5.

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?

Four short sentences, front-loaded with what is read and what is returned, then conditional parameter guidance, then the safety clause. Every sentence carries distinct information with no padding.

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 not be described, and the annotations cover the safety profile; the description fills in the version-check semantics and the trust boundary for returned content. The remaining gap is disambiguation from the many other read_* tools in the sibling list.

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 and does: section_id omission selects the main section, expected_hash enforces a version check. Only skill_id ('named skill') is left implicit, which is a minor gap for a 3-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 one named skill section, returning version, hash and dependencies. The scope word 'skill section' distinguishes it from read_document/read_resource siblings, though no sibling is named explicitly to route the agent.

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 conditional usage for two parameters ('Omit section_id for main', 'Pass expected_hash to refuse changed instructions') and a security caveat about treating saved creator content as data. However, it never says when to choose this tool over native.read_resource, native.read_document, or native.read_skill.

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