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

Annotations already declare a safe read (readOnlyHint true, destructiveHint false, openWorldHint false), yet the description goes materially further: enumeration gaps mean unknown, not absence; null is not zero; and daily captures cannot reveal actors, causes, intraday edits/reversals, or pre-collection states. These are substantive interpretation constraints an agent would otherwise get wrong, and they do not contradict the annotations.

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?

Front-loaded with what the tool returns, then view semantics, then caveats. The sentences are dense but each carries distinct information; the compressed phrasing ('Missing or incomplete enumeration is unknown, not absence') is terse enough to read as clipped rather than wasteful.

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 13-parameter, read-only history tool with an output schema and full annotation coverage, the description covers the interpretive risks (unknown vs absence, null vs zero, actor/cause limits) that the schema cannot. Remaining gaps are minor: the 90-day range cap and pagination discipline live in the schema, so their absence here is acceptable.

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?

With 100% schema coverage the baseline is 3, but the description adds genuinely new semantics: net_changes compares 'the exact start/end dates, including unchanged entities', which the schema only partially conveys via 'not every edit'. It does not add anything for limit/offset/entity_ids beyond what the schema documents.

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 uses a specific verb and enumerates the exact resources returned: daily SP/SB keyword or product-target bid, source currency, and state observations, plus scope detail ('including paused/zero-delivery entities'). It is clearly distinguishable from performance tools by naming the observed fields, though it never names the near-siblings (get_ads_change_history, get_action_history) it could be confused with.

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?

It differentiates the two views precisely ('history returns captures; net_changes compares the exact start/end dates, including unchanged entities'), which guides parameter choice. It gives no guidance on when an agent should pick this tool rather than get_ads_change_history or get_keyword_performance, so tool-level selection is left inferred.

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