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

Annotations only cover the read-only/idempotent safety profile, and the description adds substantive behavior beyond them: feed connectivity via meta.feed_connected, staleness caveats ('a connected socket does not mean each game changed this second', 'if disconnected, say the returned state may be stale'), and per-source differences in source_updated_at. This is exactly the kind of operational context annotations cannot express.

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?

Core purpose and source selection are front-loaded, and most sentences are terse and functional. The 'Developer or Production:' fragment at the start is slightly cryptic and the reporting instructions ('Always report observed_at...') are somewhat dense, but nothing is redundant.

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 carries the burden of return-value context and does so for the key fields (observed_at, meta.feed_connected, source_updated_at). It stops short of describing the per-game payload itself (teams, score fields, period formatting) and how league filtering affects results, leaving a modest gap for a live-data tool.

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 the baseline is 3; the description goes slightly beyond by contrasting the two source values' downstream behavior (PrizePicks supplies source_updated_at, Polymarket leaves it null) and by noting the league filter is optional. It says nothing additional about the required user_request parameter, so it is not fully additive.

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 specific verb+resource ('latest source-pushed game scores, period, clock and status') and explicitly distinguishes itself from sibling territory with 'These are game updates, not projection lines', separating it from get_projections/get_odds. An agent can route to it without opening a schema.

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?

Gives a concrete selection rule for the source parameter ('use source=prizepicks for PrizePicks game state; default is polymarket') and instructions on what to report back. It does not name alternative siblings such as get_game_logs or get_odds when historical or betting-line data is the actual need, so the when-not guidance is implicit.

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