Query a game library

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

The description discloses important behavioral traits beyond the annotations: invalid filter values are rejected before the request is sent, an empty result reliably means nothing matched, and sort defaults (e.g., avg-finish-time is LONGEST first). These details help the agent trust empty results and interpret sorting correctly. This goes well beyond the readOnlyHint/openWorldHint annotations.

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 description is well-structured with a core statement, examples, and a reliability note. It is somewhat verbose but every sentence adds value. The sort caveat is repeated in the schema, introducing slight redundancy, but the front-loaded purpose and examples outweigh this.

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?

Given 14 parameters and no output schema, the description covers the primary usage scenarios, example filters, and edge cases (e.g., empty result meaning, played_platform vs release_platform). It does not detail pagination behavior or return fields, but the page parameter is present in the schema. The description is sufficiently complete for a discovery tool of this complexity.

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?

Although schema coverage is high (86%), the description adds substantial semantic value: it explains that sort='shuffle' picks at random, indicates that avg-finish-time defaults to longest first, and cautions about played_platform returning nothing on backlog. The examples map user intent to parameter combinations, making abstract enums and fields meaningful.

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 clearly identifies the tool as 'the main discovery tool' for searching a user's library with 'Backloggd's full filter grammar'. It specifies the resource (library) and action (search), and sets expectations for filtering by shelf, platform, genre, year, status, or rating. This distinguishes it from sibling tools like search_games or browse_games.

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?

The description provides clear context for when to use this tool ('main discovery tool') with concrete examples (shelf='backlog' + release_platform='PS5', sort='shuffle'). It implicitly differentiates from siblings but does not explicitly name alternatives or state when not to use it. The exclusion on played_platform ('use release_platform instead unless you specifically mean this') is embedded in the schema rather than the main description.

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