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

Annotations already indicate readOnlyHint, openWorldHint, idempotentHint, and destructiveHint=false, so the safety profile is well-covered. The description adds behavioral nuances beyond annotations: it returns only the resolved ID ('fewest tokens'), fails with a machine-readable error (no partial guesses), and handles many formats. This is valuable context about error behavior and scope.

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?

Two tight sentences, every clause earns its keep: lists accepted formats, sets scope boundary, makes token cost claim, and describes error behavior. No fluff.

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?

For a single-parameter resolver tool with 100% schema coverage and comprehensive annotations (readOnlyHint, openWorldHint, idempotentHint, destructiveHint=false), the description provides sufficient behavior, scope, and error details. It's missing explicit output format documentation (e.g., what the successful response looks like), but given no output schema, it still conveys the minimal data promise clearly.

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 the schema already documents the single parameter 'id' with a clear list of acceptable formats. The description adds no new parameter-level details (no change from baseline 3). However, given the parameter count is 1 and the schema is exhaustive, the description's lack of additional param info is acceptable.

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 states it resolves Steam identifiers (steamid64, SteamID, SteamID3, hex, vanity names, URLs) and sets expectations by noting it's a pure identifier resolver with no profile data. It distinguishes from potential profile-related siblings but doesn't explicitly differentiate from steam_convert or steam_batch.

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 clarifies when to use this tool (for resolving any Steam identifier format to steamid64) and what not to use it for ('No profile data'). It implies this is the minimal, cheap option for ID resolution, contrasting with sibling tools that likely return richer data. No explicit alternatives named, but the context signals and sibling list allow inference.

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