Search apps

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so safety is covered. The description goes beyond them by disclosing a real asymmetry in results: Bazaar entries carry rating, category, installs and price when paid, while Myket entries only carry name and tagline. It does not mention throttling, empty-result behavior, or partial failure when one store errors.

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 tight sentences with no filler: what it does and returns, then how to use it, then a caveat about differing card contents. The line break mid-sentence and the colloquial 'cards' term slightly blunt readability, but nothing is wasted.

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 correctly takes on the job of describing return fields and their per-store variance, which is the main thing an agent needs here. What remains thin is failure and edge behavior — zero-hit queries, one store failing while 'both' is selected — for an openWorld search tool.

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%, with page size, limits, language and the store enum all documented inline, so the schema does the parameter work. The description adds only indirect meaning — that the 'store' choice changes which fields appear in results — and nothing about pagination depth or per-store page sizes. Baseline 3 applies.

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) plus the exact resource (apps and games across Cafe Bazaar and/or Myket) and names what comes back (package names, ratings, store URLs). That is enough for an agent to separate it from ap_app (lookup), ap_top (rankings), ap_similar (related) and ap_compare without opening any schema.

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?

'Use first to find a package name' gives a concrete sequencing rule that ties this tool to the downstream ap_app/ap_compare workflow. It stops short of stating when NOT to use it (e.g. when the package name is already known), so it falls one step shy of the top mark.

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