pr_skill

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

No annotations are provided, so the description carries the full burden. It discloses the mode behavior (router vs. single reference) and enumerates topics, but says nothing about output format, size, caching, or what happens with an invalid `doc` value. For a read-only reference tool the risk is low, but the disclosure is only partial.

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, each front-loaded with the mode it describes, with no filler. The parenthetical list of AI tools is long but functional since it signals coverage. Slight density cost, but nothing reads as wasteful.

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?

For a one-optional-parameter reference lookup with no output schema, the description covers what the tool returns and when to call it. The main residual gap is that the mapping from `doc` values to actual content is not spelled out, so an agent picking 'combos' or 'masking' is guessing from the schema alone.

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 schema already lists the valid `doc` values. The description adds real meaning beyond that by explaining what the absence of `doc` yields (the router) and by characterizing the content of the reference set (AI tools, multi-tool recipes, gotchas). It does not map individual enum values like 'combos' or 'timeline-automation' to topics, leaving that to inference.

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 clearly states this is a skill/reference retrieval tool with two modes: no `doc` returns the router (workflow order, capability limits, which reference to read), and `doc` returns a single topical reference. The verb is implicit ('read it') rather than explicit ('retrieve'), but an agent can still tell what it gets. It does not distinguish itself from siblings like pr_catalog or pr_do, which also sound like lookup tools.

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?

Strong usage trigger: 'read it at the start of any Premiere task beyond a single read or edit' gives a concrete when-to-use condition and an implicit exclusion. It also explains the two branches (router vs. one reference). It stops short of naming sibling alternatives for cases not covered here.

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