adobe_catalog_call

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

The annotations already state readOnlyHint=false, destructiveHint=false, and openWorldHint=false, so the safety profile is partly covered. The description adds the dispatch mechanism and an argument shape, but says nothing about what happens with an unknown or misspelled tool name, whether the arguments are passed through unchanged, or whether the call fails loudly; for an arbitrary dispatcher that is meaningful missing context.

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?

A single front-loaded sentence plus an inline example; nothing is wasted. It is arguably too terse for a generic dispatcher, but that is a completeness gap rather than verbosity.

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?

Given a nested free-form parameter, zero schema descriptions, and no output schema, the description should at minimum point at how to obtain valid tool names and sketch the return payload. It covers the call shape and nothing more, leaving an agent that has never seen a catalog name with no supported path to a first correct call.

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 0% and there are 2 parameters, one of which is a free-form nested object, so the description has to carry weight. The example usefully shows that `arguments` is an untyped pass-through map matching the target tool's own signature, but it never says where a valid `tool` value comes from or whether the 'pr1__' prefix is required.

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 specific verb and resource: it dispatches a call to a tool hosted in a bundled community MCP, and the inline example ({tool:"pr1__add_transition", arguments:{...}}) makes the indirection concrete and distinguishes it from the direct per-app tools like pr_applyTransition. It does not, however, distinguish it from its closest siblings adobe_catalog_describe, adobe_catalog_search, and adobe_catalog_libraries.

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?

Usage is only implied: the example shows that the target tool is identified by a prefixed name, which hints that discovery is a prerequisite, but the description never says to look up names via adobe_catalog_search or adobe_catalog_describe first, nor when to use a direct sibling (e.g., pr_openSequence) instead of routing through the catalog.

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