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

The description discloses important behavioral traits beyond annotations: it uses a cache snapshot (no live Steam call), may be partial, and provides token cost per detail level. Annotations already declare readOnly and idempotent, which the description confirms. This adds value by explaining data freshness and response format implications.

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 three concise sentences with no wasted words. First sentence states purpose and key behavioral trait (cache snapshot). Second sentence explains detail levels and their cost. Third sentence gives explicit recommendation. Each sentence earns its place, and the structure front-loads the most critical information.

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 explains short and medium output formats and states that full mode returns raw Steam objects. This gives adequate expectations for return values. The limit parameter is documented in the schema but not repeated in the description, which is acceptable given schema coverage. The partial snapshot note fills a gap. Slightly more detail on limit behavior or pagination would push to 5.

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 100%, so baseline is 3. The description adds significant value for the 'detail' parameter by specifying exact output structures (short: steamid64 array, medium: steamid64+personaname, full: raw Steam objects), which is not in the schema. It also recommends 'short' for efficiency, aiding parameter selection beyond schema descriptions.

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 the tool retrieves 'Known friends of a player from the platform's snapshot of the public Steam friend graph.' The verb 'retrieve' is implied, and the resource is 'Steam friends.' It distinguishes itself from siblings like steam_profile and steam_summary by specifying it deals with the friend graph, not individual profiles or summaries.

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 offers guidance on the detail parameter ('Use short unless you need names') but does not explicitly state when to use this tool versus sibling tools. While the tool's name and purpose imply it for friend list retrieval, no alternatives or exclusions are mentioned, leaving the agent to infer context from the sibling list.

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