refresh_data

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

Annotations already declare readOnlyHint=false and idempotentHint=false, so the agent knows this mutates state and is not repeat-safe. The description adds real context beyond that: it discloses the side effects (logging today's forecasts, detecting signals) and the specific return payload (rostered injury changes, newly caught signals).

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, front-loaded with the action and then the return value. The parenthetical domain list is dense but each item earns its place by defining sync scope; no filler.

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 correctly carries the return burden by naming the two things it returns. Given the mutation semantics flagged by annotations, it is complete enough for an agent to invoke it, though a note on cost/latency or repeat-run behavior would round it out.

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 tool takes zero parameters, so there is nothing for the description to disambiguate; the 4 baseline applies.

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 ('Run the daily ESPN sync') and enumerates the exact data domains it covers (schedule, box scores, averages, injuries, news, projections). This clearly marks it as the ingest/refresh operation rather than a read tool, though it never names a sibling to differentiate against.

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?

'Daily' implies a once-per-day cadence, which hints at when to run it, but there is no explicit when/when-not guidance and no reference to the many sibling read tools (injuries, news, snapshot, signals) it complements.

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