Muretai Catalog

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

Annotations cover the safety profile (readOnlyHint=true, openWorldHint=false), and the description still adds real behavior: two provenance classes of result, the fact that unclaimed shops are search-only with no entry point, and what each result carries. That is genuinely useful routing context. It stops short of 5 by not covering pagination or total-count behavior.

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, no filler, with the corpus definition front-loaded before the return-value explanation. The inline parenthetical about provenance is a little dense but is doing real semantic work rather than padding.

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 takes on the return-shape burden and discharges it by naming the four fields each result yields. Combined with the provenance rule and 83% schema coverage on six optional parameters, an agent has enough to call this correctly.

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 83% and every parameter except 'limit' carries its own description, so the schema does the explaining. The description adds only the loose notion of 'matching products', saying nothing about how q is tokenized, how tags must ALL match, or how max_price interacts with unknown prices. Baseline 3 is appropriate.

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 ('Search shops') and immediately bounds the corpus: shops with a signed Agent Card plus unclaimed public listings. The provenance distinction ('unclaimed': search-only, no door) makes the scope precise. It is not a 5 only because there are no siblings to differentiate from, so the differentiator clause has nothing to contrast against.

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 implied through the follow-on step ('go straight to that shop's Agent Entry with a signed request'), which tells the agent this is a discovery entry point rather than a transactional call. There is no explicit when-not-to-use guidance, no statement about what to do when zero results return, and no mention of how to reach unclaimed shops given they have 'no door'.

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