adobe_catalog_search

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 the important behavioral fact that this only searches a bundled community catalog and that results are not directly invocable without a describe step. It doesn't say what fields are matched (name vs. description) or how many results return, which keeps it from a 5.

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 sentences, front-loaded with the resource and scope, then the usage rule. The parenthetical tool counts are dense but genuinely informative for choosing a library; nothing is redundant with the schema.

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 still conveys that results are catalog entries which must be described before being called, which is the key completeness gap for a search tool. Minor omissions remain: result shape, pagination/default limit, and whether search is lexical or semantic.

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%, so the description must compensate. It does partially by expanding what the library codes mean (ae1/ae2 = After Effects, pr1 = Premiere, ps1 = Photoshop with Firefly, ai1 = Illustrator), but it never explains 'query' matching semantics, the 'app' vs 'library' distinction, or what 'limit' controls or defaults to.

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 (search) and a precisely bounded resource (~550 extra tools from the bundled community Adobe MCPs), and quantifies each bundled library (ae1/ae2, pr1 280 tools, ps1 128, ai1 66). This clearly separates it from siblings like adobe_catalog_describe and adobe_catalog_call, which operate on a single already-known tool.

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 an explicit trigger ('Use when no native tool fits') and then the exact follow-up sequence 'adobe_catalog_describe → adobe_catalog_call'. The agent knows both when to reach for this and what to do with the results, and the exclusion of native tools is stated outright.

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