ps_getDescriptor

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds that output is JSON and shows a real target shape, but says nothing about what happens with an invalid target/property token or how large/unwieldy the returned descriptor tree may be — the main practical failure mode for this tool.

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 purpose is front-loaded in the first clause and the example sits immediately after it; almost every token carries information. It is a dense run-on sentence, but there is no filler or restatement of the name.

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 should say more about the returned JSON shape than 'as JSON' — an agent cannot tell whether to expect a flat property map, a nested descriptor, or raw AM tokens. For a two-parameter read tool it is otherwise serviceable, but the return-value gap is the notable omission.

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 0% for the 2 parameters, so the description must carry the meaning. It does give a concrete 'target' example and names one optional property ('layerEffects'), which is real added value, but it never explains the valid _ref/_enum/_value vocabulary or what property names are accepted, leaving the agent guessing beyond the single sample.

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?

Opens with a specific verb+resource: 'read Action Manager properties (application, document, layer, channel...) as JSON'. It also differentiates itself from the nearest sibling by saying it discovers what ps_actionManager can set. Slightly diminished by 'Action Manager' jargon an agent may not resolve, but the resource scope is explicit.

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?

'Discover what ps_actionManager can set' gives a concrete use-case and effectively routes the agent toward this read tool before invoking the setter. It does not state exclusions or when a plain state tool (ps_getState) would be preferable, so it falls short of a full when/when-not pair.

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