Get rank history

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

Annotations already declare readOnly/openWorld=false/destructive=false, so the safety profile is covered. The description goes well beyond them by explaining how to interpret a null position under different observation_completeness states and by classifying error_code values with retry policy — real operational context an agent cannot get elsewhere. It stops short of stating pagination ceilings or auth requirements.

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 the action, then dense interpretive rules in three tight sentences. Every clause about coverage/error_code earns its place given there is no output schema, though the opening sentence could have done slightly more work before the interpretive block.

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 must explain return semantics, and it does so well: status, observation_completeness, position nullability, and error_code taxonomy. The remaining gap is input-side — no format guidance for the date, cursor, or limit parameters.

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 only 29% (keyword_id and project_id only), so the description must carry the rest. It gestures at 'date, status, and pagination filters' but gives no format for since/until (maxLength 80), no cursor semantics, and no hint about the limit ceiling of 200. It partially compensates but leaves most parameters underspecified.

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?

Opens with a specific verb+resource: 'List historical rank checks for a keyword,' and enumerates the filter axes (date, status, pagination). This is clearly distinct from siblings like list_rank_check_runs or get_rank_check_result, though it never names an alternative to differentiate itself explicitly.

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?

Usage is implied by the filter axes and the retry rule ('retry only for provider_rate_limited or provider_transient'), which is genuinely actionable. However, it never says when to choose this over export_rank_history or get_rank_check_result, nor any prerequisites such as which project scope is required.

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