ps_skill

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

With no annotations, the description carries the burden and does well: it discloses that the no-`doc` call returns a router-level guide, that `doc` returns exactly one reference, and it enumerates the substantive topics each contains (generative tools, retouch, selection/masking, gotchas, script limitations). It does not explicitly state that the tool is read-only with no image mutation, but the 'read it' framing and documentation-only content make that clear enough.

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?

It is dense but front-loaded: the two modes are introduced immediately and the reference topics are enumerated compactly. The single run-on sentence with many comma-separated topics is slightly hard to parse, which keeps it from 5, but every clause carries routing information.

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 documentation tool with no output schema, the definition is complete enough: it says what each mode returns, when to invoke it, and what topics are available. It could go further by suggesting the sequence (read router first, then a specific doc) or output format, but those are minor for a knowledge-lookup tool.

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 already 100%, so the baseline is 3. The description adds meaning beyond the schema by mapping the `doc` slug values to their subject matter — e.g. 'generative' covers Generative Fill/Expand/Remove and credits, 'gotchas' covers pitfalls — so an agent can pick a reference without guessing from the slug alone.

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 makes clear this is a documentation router for Photoshop: with no `doc` it returns a guide covering tools, order of work, addressing, and script limits; with `doc` it returns one named reference. The two-mode behavior is explicit and an agent can distinguish it from action-oriented siblings like `ps_do` or `photoshop_generative_fill`. It never names a sibling directly, so it stops short of 5.

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?

It gives an explicit trigger — 'read it at the start of any Photoshop task beyond a single read or edit' — and an explicit exclusion for trivial single operations. That is exactly the routing guidance an agent needs before choosing between this docs tool and the numerous action tools.

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