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

Annotations already cover readOnly/idempotent/non-destructive, and the description adds genuinely non-obvious context: the skill text is creator-authored and therefore untrusted, with an explicit instruction-following caveat. It stops short of noting any rate limits or what happens when a handle/slug pair does not exist.

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 tight sentences: the first front-loads what the caller gets, the second front-loads the safety rule. No filler, no restatement of the name or title.

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 needn't explain return shape, yet it still previews the contents. Purpose, contents and usage caution are all covered; only failure behavior for unknown handles/slugs is absent, which is a minor gap for a simple two-param read.

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 both parameters are documented there, including the @handle format and the reference to market_find_skills for the slug. The description adds no further meaning about either parameter, so the baseline 3 applies.

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 concrete verb (read) and resource (one skill) and enumerates the payload — description, version, files, SHA-256, install steps, outputs — which implicitly contrasts with the plural listing tool market_find_skills. It never names that sibling explicitly, so an agent must infer the pairing from 'One skill in full'.

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 real usage context: 'read it before you install it' establishes the pre-install inspection workflow, and the follow-only-on-request rule sets a policy boundary. It does not name market_find_skills as the way to obtain the handle/slug, so the discovery path is left implicit.

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