cards_find

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

With no annotations, the description carries the full burden and mostly delivers: it enumerates returned fields, states BCX is guaranteed only on this per-instance route, clarifies player is owner attribution not donor provenance, and discloses the 100-row and 256 KB bounds plus non-caching. It stops short of explicitly stating the operation is read-only or whether ids must belong to one player.

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?

Every sentence carries real information, but the ordering is poor for tool selection — it opens with card_set/edition output semantics before stating what the tool does, then interleaves parameter encoding, return fields, and limits. Dense and somewhat meandering, though not padded.

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?

There is no output schema and no annotations, and the description covers the essentials: what a matched record contains, the BCX guarantee, provenance semantics, error behavior for bad encodings, and result-size limits. Only authentication/access requirements are unaddressed, which 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 coverage is 0% (only a bare string with minLength), so the description must compensate and does: it specifies the encoding as a single comma-separated string of full per-instance UIDs, confirms order is preserved, and rules out repeated and bracketed forms with the observed failure modes for each. This is meaningfully more than the schema provides.

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 specific verb and resource — 'Look up per-instance card records through GET /cards/find' — and explicitly scopes it against definition routes ('BCX is therefore promised for this per-instance route only; it is not a claim about definition routes'), which helps distinguish it from siblings like cards_get_details. The purpose is clear but is buried midway through output-field discussion rather than front-loaded.

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?

It gives the condition that ids must be one comma-separated string of full per-instance UIDs and rules out repeated/bracketed/JSON-array encodings, which is strong usage guidance for this specific call. However, it never says when to choose this tool over cards_collection or cards_get_details — the sibling routing is only an oblique contrast with 'definition routes'.

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