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

Annotations already mark this as read-only, so the description's main job is to disclose behavior beyond safety. It does that by specifying the return shape (`pick`, `intent` hits, `motion` hits, ranked `matches`) and the payload contents of cards. It does not discuss edge cases like empty results or ranking details, but these are not critical given the read-only annotation.

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 description is compact: three sentences front-load the purpose, then cover input, output, and routing. The phrase 'Two-query catalog match' is slightly jargon-heavy and unexplained, which costs it a 5, but every sentence otherwise earns its place.

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 compensates well by spelling out the return fields and card contents. Parameters like `kind` and `limit` are left to the schema, which is acceptable, though a note about what `pick` means in more detail or empty-result behavior would make it fully complete.

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 100%, so the schema already carries the burden of documenting all 7 parameters, including the inference behavior for intent and motion. The main description adds the 'and/or structured filters' framing and an example query, but this is marginal value rather than necessary compensation.

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 action and resource: 'catalog match' against Cronus UI catalog tags, with both free-text and structured-filter inputs. It differentiates itself from siblings by explicitly saying cards do not carry source and directing source retrieval to get_component.

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?

The description gives clear when-to-use context ('low-context agents', free-text and/or structured filters) and an explicit when-not: 'Cards carry description... not source.' It names the alternative action ('Fetch source with get_component only after picking a name'), so an agent knows exactly how to route after matching.

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