Architecture: Catalogue

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

Beyond the readOnlyHint annotation, the description discloses the exact catalogue size (20 items: 13 furniture, 7 sanitary), clarifies that sizes are nominal catalogue dimensions rather than standards values (flagged per-row via size_basis), and states the two refusal conditions with the returned list. This is meaningful behavioral context not present in structured fields.

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 row-columns list is front-loaded and dense. The middle paragraph on size_basis straddles usefulness and verbosity, but it earns its place by preventing an agent from treating the sizes as standard values, and the refusal sentence is compact.

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 an output schema present, the description need not explain return formatting, though it usefully summarizes columns. It covers the catalogue size, size-basis caveat, and refusal cases. The main missing piece is when to prefer this tool over related architecture tools, but for a simple read tool that gap is minor.

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 lang, query, and family are already fully documented, including query's case/diacritic-insensitive word matching. The description adds only the refusal behavior for unsupported family and lang values, which slightly reinforces the valid-input boundary but does not add new semantics.

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 states a concrete read operation and enumerates the returned row fields (name, family, labels, nominal size, block name, layer), so an agent knows this retrieves the architecture catalogue. It does not explicitly contrast itself with the sibling arch_catalogue_insert, but the listing/read nature is clear from the name and content.

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?

There is no explicit 'when to use this vs alternatives' guidance. The refusals paragraph describes error behavior for invalid family/lang, not selection criteria, and no sibling tool is named as an alternative. Usage is only implied by the tool name.

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