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

Annotations already carry the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description still adds real value by disclosing data-quality behavior—decimal quantities, unknown values, source dates and incomplete coverage are surfaced rather than smoothed over, and no re-matching or balance lookup happens.

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 with no filler, front-loaded with the core action and scope. The phrase 'exact validated saved historical report' is slightly dense jargon but is the substance of the answer, not padding.

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?

An output schema exists, so return shape need not be explained; annotations cover safety. The description supplies the snapshot semantics and quality caveats that an agent needs to interpret the report correctly. The remaining gap is parameter-level guidance, which neither the schema nor the description provides.

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% across 3 parameters, so the description must compensate. It hints at pagination ('Page the ... report') and ownership scoping ('owned wallet'), which loosely maps to cursor/limit and walletId, but gives no detail on cursor format, page size bounds, or wallet identifier expectations.

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 ('Page'/'Read') and resource ('saved historical report for an owned wallet'), and explicitly rules out live behavior: 'No new matching, refresh or balance lookup occurs.' An agent can tell this returns a stored snapshot rather than computed positions, though the name 'get_wallet_positions' vs the description's 'report' framing is a minor mismatch.

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?

Clear context: use for an owned wallet's already-saved historical report, and the closing sentence tells the agent this is not a refresh/recompute path, which is the key usage distinction. No sibling alternative is named, and the failure mode for a wallet the caller doesn't own is unstated.

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