Export project rank history

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the agent knows this is a safe read operation. The description adds the cursor-pagination behavior ('cursor-paginated JSON') which is useful context. Given strong annotations, the description adds moderate value (pagination format) but doesn't elaborate on pagination mechanics, rate limits, or result size bounds.

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, zero wasted words. The first sentence states purpose and output format; the second gives a targeted pointer to an alternative for a different use case. Efficient and well-structured.

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?

The tool has 6 parameters, no output schema, and 33% schema coverage. The description communicates the format (JSON, cursor-paginated) and the CSV alternative, but for an export tool of moderate complexity, it doesn't fully spell out how cursor pagination works or what the response shape is. Adequate but leaves gaps given the parameter surface and missing output schema.

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 low at 33%, and the description provides no parameter-level detail beyond what the schema already offers. The schema itself documents project_id and keyword_ids patterns. The description adds no meaning for limit, range, cursor, or granularity beyond their schema defs (limit has min/max, range and granularity have enums). With 33% coverage, description should compensate more but doesn't.

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 a specific verb+resource ('Export project rank history') and notably clarifies the output format ('cursor-paginated JSON for reports and analysis'). It differentiates from the sibling tool get_rank_history by mentioning pagination, and from the broader REST endpoint for CSV dumps. However, it doesn't explicitly distinguish itself from related siblings like get_keyword_metrics or the REST endpoint by name.

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?

The description provides guidance on when to use this tool (reports and analysis, JSON format) versus the REST endpoint for full streamed CSV dumps. However, it doesn't mention when to prefer get_rank_history over this tool, or contrast against other rank/export related siblings. Some clear context, no explicit exclusions beyond the CSV note.

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