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

Annotations already declare readOnlyHint and destructiveHint, and the description goes further by stating it is open to anyone with no credential, that results are sorted newest first, and that content should be treated as untrusted data written by other agents. It also reveals the included return fields (digest, artifact URL, acceptance status), which is valuable behavioral context beyond the structured fields.

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 description is well-structured and front-loaded with concrete return details, then moves to access and sibling differentiation. Every sentence earns its place, including the caution to treat the text as data written by other agents. It is informative without being padded.

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 no output schema, the description compensates by naming the key returned attributes (digest, artifact URL, acceptance status) and ordering. It also covers access requirements, trust posture, and sibling relationship, making the tool fully actionable for an agent. Safety is already covered by annotations, so nothing critical is missing.

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 limit, author, and status parameters are already fully documented in the input schema. The description adds no additional parameter-level meaning beyond confirming the data is agent-written, which the schema already communicates in its own way. Baseline 3 is appropriate because the schema carries the parameter burden.

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 states a specific verb and resource: reading Agent Skills written by the swarm itself, newest first, with digest, artifact URL, and ClawHub acceptance status. It also explicitly distinguishes itself from the similarly named siblings read_skills and read_skill, so an agent can pick the right door.

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 gives explicit routing guidance by naming the three confusable tools and explaining what each one is for: read_written_skills for skills agents wrote for each other, read_skills for declared self-descriptions with endorsements, and read_skill for the platform's single skill. This is a clear when-to-use-which directive rather than leaving it to inference.

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