cards_get_details

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

No annotations exist, so the description carries the full burden and does so thoroughly: it discloses the server-side 256 KB size bound and the refusal behavior for unfiltered calls, notes this is a server choice rather than an upstream rule, states 24-hour caching of filtered metadata, explains provenance reports the route and original fetch time, and enumerates returned fields plus explicitly absent ones (no BCX, donor or account-attribution). This is exactly the kind of context annotations would otherwise supply.

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 content is dense and mostly earns its place, but it is long for a one-parameter tool and not well front-loaded: it opens with a secondary 'editions' data caveat rather than the primary purpose. The refusal explanation is also restated twice ('refuses an unfiltered call...', then 'That refusal is this server's size-based choice...'), which is redundant.

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 and 0% param coverage, the description supplies the missing return-field list (id, name, color, type, sub_type, rarity, drop_rate, per-level stats, abilities, editions, total_printed, distribution), caching and provenance behavior, and the critical filter requirement. It is nearly complete; only the set of valid `type` values is left unspecified.

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% and the single `type` parameter has no description in the schema, so the description must compensate. It explains that `type` is a real upstream filter (type=Summoner returned 107 rows vs 1101 bare) and that providing it is required in practice due to the size bound. It stops short of listing valid type values (no enum), leaving some ambiguity.

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+resource ('List the card-definition rows returned by GET /cards/get_details') and explicitly distinguishes itself from siblings by telling the agent to use `card_set` from cards_collection or cards_find for the main set. The opening caveat about numeric `editions` muddies the lead slightly, but the core purpose is unambiguous.

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?

Gives a concrete usage condition: an unfiltered call is refused by this server because the ~1.17 MB response exceeds the 256 KB bound, so the agent must provide `type`. It also names alternative tools (cards_collection, cards_find) for main-set card_set lookups. No explicit 'when not to use' beyond that, so a 4 rather than 5.

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