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

Annotations already declare readOnly, idempotent, non-destructive, so the safety profile is covered; the description goes well beyond them. It discloses at-least-once delivery with the exact de-duplication key (race_id, runner number, bookmaker, updated_at), the 60-second default window, the 30-minute cursor expiry, credit cost, and plan availability — precisely the facts an agent needs to consume the stream correctly.

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?

Four declarative sentences, front-loaded with the delta-feed purpose, then the call protocol, then delivery semantics and cost. Every sentence carries information an agent would otherwise have to guess. Slight overlap with schema text on the 30-minute refusal keeps it from a 5.

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 delta-pull tool with an output schema, this covers the hard parts: bootstrap behavior, cursor handoff and expiry, duplicate handling, cost, and the fixed 60-second initial window. An agent could implement a correct polling loop from the description alone.

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 baseline is 3; the description earns above that by explaining the cursor lifecycle (omit first, feed back within 30 minutes) and the default window that applies when cursor is absent. Country and categories get no treatment in the description, but their schema text already enumerates everything needed.

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?

States a precise verb-and-resource combination: 'Only the racing prices that moved since your last call' — a delta feed rather than a snapshot. That framing distinguishes it from snapshot-style siblings such as odds_board or race_odds, though it never names an alternative explicitly, so differentiation is left to inference.

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 call protocol is spelled out: omit cursor on the first call (last 60 seconds), pass next_cursor back within 30 minutes. That is clear operational guidance. It stops short of saying when an agent should choose this over price_history, bulk_datasets, or polling odds_board, so the when-to-use-vs-alternatives gap remains.

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