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

Annotations declare readOnlyHint, idempotentHint, and non-destructive, which the description does not contradict. It adds valuable behavioral details: that opening is the first snapshot regardless of how far before kickoff, that closing is the last snapshot at or before commence_time, that the archive starts 2026-04, and that the free tier returns a redacted structure with an upgrade pointer. These disclosures go beyond the 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 detailed but efficiently front-loads the core purpose and key distinctions before diving into nuances. It is longer than typical but each sentence adds critical value, including a caveat about points vs prices and free-tier behavior. No redundancy, though it could be trimmed slightly without losing meaning.

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 read-only tool with two required parameters and optional filters, the description covers everything an agent needs to select it correctly: it explains the return data (opening/closing, prices/points), the lookback behavior, the archive start caveat, the point comparison guidance, and the free-tier redaction. No output schema is needed given the detailed explanation.

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 50%, but the description explicitly defines the semantics of key parameters like opening_window (with example value 14 and 'all'), and explains how period and bookmakers are used. It does not detail markets, but the overall context clarifies the primary parameters. This compensates well for the partial schema coverage.

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 returns opening and closing lines per (book, market, outcome) for an event, with explicit definitions of both data points. It distinguishes itself from related tools by framing it as a canonical CLV-tracking helper and contrasts with fetching full history, making it unique among siblings like propline_get_odds_history and propline_export_odds_history.

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?

It provides clear when-to-use guidance: for CLV tracking, comparing points as well as prices, and understanding opening_age and archive start limitations. It does not explicitly name alternative tools or state when not to use it, but the context strongly implies it is preferred over history-fetching for CLV measurements.

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