get_draft_picks

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

Annotations already cover readOnly, idempotent, and non-destructive. The description adds valuable behavioral context: it returns only 'completed picks' (a filtering behavior) and mentions a 'player metadata snapshot,' indicating the data is a point-in-time record. This goes beyond the annotations and helps the agent understand the semantics of the returned data.

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 compact, with the primary purpose front-loaded in the first sentence. It uses two short paragraphs: one for what it returns and one for usage and parameter source. There is no redundant phrasing or filler—every sentence adds 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?

For a simple list tool with a single parameter, the description covers the input source, output content, and typical use cases. It does not mention ordering or pagination, but those are often not critical for such an endpoint. The absence of an output schema is compensated by listing the key fields, making the description sufficiently complete for an agent to invoke the tool correctly.

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?

The input schema already fully describes draft_id with a clear description. The tool description adds a hint on where to obtain the draft_id (from get_league_drafts or get_user_drafts), which is useful but not essential beyond the schema. Since coverage is 100%, the description's extra hint provides marginal value, aligning with the baseline of 3.

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 opens with a specific verb and resource: 'Return all completed picks from a Sleeper draft.' It explicitly lists the fields returned, making the tool's scope unambiguous. It differentiates from siblings like get_draft (draft metadata) and get_draft_traded_picks (traded picks) by focusing on completed picks and referencing how to obtain the draft_id.

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 clearly states that draft_id should be obtained from get_league_drafts or get_user_drafts, and it lists concrete use cases ('draft recaps, team-by-team results, reaches, values, and board reconstruction'). While it does not explicitly say when not to use this tool or compare it with get_draft, the guidance is sufficient for an agent to decide when to call it.

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