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

Annotations already cover read-only, idempotent, non-destructive, closed-world. The description adds genuinely non-derivable behavior: no API key, no quota, and the crucial fact that some datasets return fabricated rows marked sample:true while others return frozen real captures. It does not describe the response envelope or how generated_at is surfaced, but the risk profile is well disclosed.

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?

Three tight sentences, front-loaded with the access constraint and the data-provenance caveat, with no filler. Every sentence carries operational information an agent needs before calling.

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 keyless sampling tool with no output schema and ten enum choices, the description covers provenance and auth well but leaves the per-dataset behavior of eight enum values and the limit semantics undocumented. An agent still has to guess what 'events' or 'coverage' samples will contain.

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 0%, so the description must compensate and it only partly does: it explains the synthetic-vs-frozen distinction for exactly two of the ten enum values (dfs and pick6), leaving events, odds, history, pick6-history, stats-* and coverage unaddressed. The limit parameter (1-100) is never mentioned at all.

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 states concretely what comes back: sample rows that are either real captured rows frozen at generated_at or invented rows flagged sample:true, usable without a key. It is clearly different from the sibling get_dfs_* / get_pick6_* / get_stats_* tools, though it never names one of them explicitly as the production alternative.

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?

'For wiring up a parser' gives a clear when-to-use context (integration work, not production reads), and 'never report it as current data' gives an explicit exclusion. It stops short of naming the real-data sibling to use instead once the parser works.

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