ygo_find_counters

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

With no annotations supplied, the description carries the full burden and does most of it: it discloses the upstream source, that results are community evidence rather than rulings, that each entry includes a source URL, and what fields are returned. It does not say what happens when neither filter is supplied or when no counters exist, which is the remaining gap for a filter-based read tool.

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?

Front-loaded with an imperative "USE THIS for" plus the triggering questions, then source and return shape, then scope caveats, which is the right order for an agent. Slightly long and repeats the anti-memory instruction already implied by the preceding sentences, but no sentence is off-topic.

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 properly fills that role by enumerating returned fields (counter cards, impact, chokepoints, author explanation, source URL). It is nearly complete; only the zero-filter / empty-result behaviour is unstated, which is minor for a 3-parameter read 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%, so all three parameters are already documented, which sets the baseline at 3. The description reinforces the key distinction — filtering by an archetype being countered versus by a card that appears as a counter — but adds no format, matching, or partial-name detail beyond the schema.

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 first sentence gives a concrete verb and resource (returns published counter strategies) plus the exact user questions it answers, and the second sentence names the data source (Master Duel Meta) and the shape of an entry (counter cards with impact, chokepoints, author explanation). It is clearly distinguishable from siblings like ygo_find_combos or ygo_find_community_decks.

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?

Explicit when-to-use triggers are quoted ("how do I beat this deck / what counters it / which card stops this combo"), a boundary is drawn against ygo_judge_card for verified card behaviour, and it states a preferred ordering ("call this tool first", "do not answer from memory"). Nothing about routing is left to inference.

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