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

Annotations already declare read-only/idempotent, but the description adds substantial behavior: code-fence headings are ignored, matching is first-exact ATX heading and case-insensitive, offsets are UTF-16 units, output is capped with next_offset continuation, and the parent skill must belong to the playbook.

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 core action and its scoping constraint are front-loaded, and later sentences supply the matching, pagination, and permission rules. It is dense and packs several rules together, but no sentence is filler.

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?

With an output schema present, the description need not describe return values, and the remaining unknowns an agent would care about — file selection, section matching, pagination, size caps, and the playbook ownership precondition — are all covered.

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 goes beyond it by explaining that section matches the first exact ATX heading case-insensitively with code fences ignored, and by clarifying that offsets count UTF-16 string units and chain from next_offset.

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 with scope: 'Read exactly one skill file, optionally just one Markdown heading and its subsections.' It also distinguishes itself from the sibling get_skill by directing the agent to that tool's attachment manifest as the source of filenames.

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?

Explicitly tells the agent where filename values come from (get_skill's attachment manifest, or SKILL.md for main instructions) and what section values must match. It does not state any when-not-to-use condition or contrast with other read tools like read_canvas, so it falls just short of full routing guidance.

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