get_predictions

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

With no annotations provided, the description carries full transparency burden. It discloses the refresh interval (~10 minutes), the data source (confirmed lineups), and the conceptual approach (lineup-aware vs. team form). It does not detail rate limits, return shape, or edge cases, but for a simple read operation it gives sufficient behavioral context.

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 sentences, each with a distinct purpose: sentence 1 defines the core output and refresh frequency, sentence 2 covers the optional filter and provides a key conceptual contrast. No filler or redundancy.

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?

The description is complete for a single-parameter, read-only predictions tool: it covers what, when, source, refresh, filter, and conceptual distinction. An output schema exists to handle return values, so no description of the output is needed. The only minor gap is lack of explicit sibling alternatives, but that's already addressed in usage guidelines.

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 description explicitly explains the sole 'league' parameter as an optional filter by name/code, which is not covered in the schema. This fully compensates for the 0% schema coverage for this parameter, though it omits example values or format hints.

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 provides win/draw/win probabilities for upcoming matches based on confirmed lineups, with a refresh cadence and optional league filter. This is a specific, actionable function that also distinguishes itself from form-based prediction tools.

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 gives clear context for when the tool is relevant (upcoming matches, confirmed lineups, lineup-aware predictions) but does not explicitly name alternative tools or exclusion criteria. The 'not just team form' comment implies a distinction but doesn't offer direct sibling guidance.

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