PuzzleGame.win

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), but the description adds substantial behavioral context beyond them: GAME_NOT_FOUND semantics for missing/unapproved/inactive/unplayable records, alias resolution to the canonical sourcePage, and explicit negatives about what is not returned (invented instructions, asset downloads, verified scores, compatibility guarantees).

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?

Three dense sentences, front-loaded with the core action and inputs before the caveats. Every clause carries information, though the closing list of exclusions is long and could be trimmed.

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?

An output schema exists, so return values need not be described; the description instead covers the areas structured fields cannot: the failure mode, alias normalization, and the limits of what the returned data guarantees. Nothing material is missing for correct invocation.

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 0%, so the description must carry parameter meaning, and it only partially does: it establishes provenance ('from search_games') and that aliases resolve to sourcePage, but says nothing about the provider enum values or slug format constraints that live only in 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?

States a specific verb and resource ('Get an approved, active catalog game') and names the exact inputs (provider and slug from search_games). It is clearly distinguishable from the sibling search_games, which is the discovery tool that supplies these identifiers.

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?

Explicitly routes the agent from search_games into this tool by telling it where provider and slug come from, establishing a clear follow-up workflow. It stops short of stating when *not* to use it (e.g., bulk retrieval), so 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.

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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, and the description adds substantial extra behavior: canonical deduplication per provider/slug, a deterministic ordering rule (exact title match, then featured/quality/title), case-folding semantics, and the absence of a live health check. This is exactly the beyond-annotations context the bar asks for.

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?

Five short sentences with no filler; the core search scope is front-loaded before the ordering, routing, and caveat details. Dense but each sentence contributes a distinct fact, though a couple (case-folding method, ordering internals) sit near the limit of what an agent needs before calling.

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?

An output schema exists, so return-value documentation is not required, yet the description still supplies the ordering and dedup semantics an agent needs to interpret results. Combined with the routing hint to get_game_details and the explicit no-health-check caveat, nothing needed to call this correctly is missing.

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 only 20%, so the description carries real weight, and it does: 'literal text' meaning for query, exact catalog filters for category and provider, plus the empty-query browse behavior. page/limit are left to the schema's own minimum/maximum/default constraints, so not every parameter is elaborated, but the ambiguous ones are.

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 with explicit scope: 'Search all approved, active catalog games by a literal title, slug or description substring.' It also distinguishes the retrieval mode ('literal ... using SQLite case folding (ASCII case-insensitive)'), separating it from a semantic search. An agent can tell it apart from get_game_details without opening either 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?

Explicitly covers the empty-query case ('Empty query browses the catalog') and routes the agent forward ('Use the returned provider and slug with get_game_details'). It also pre-empts a wrong assumption by noting no live provider health check is performed. It does not state when NOT to use this tool versus get_game_details for discovery-style queries, so it stops short of full when/when-not coverage.

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