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

With no annotations, the description carries the full burden and does well: it discloses page-size caps (10,000 observation rows / 1,000 cross-signal insights), newest-first ordering, and the truncated/next_cursor continuation protocol including how to resume. It omits auth requirements and rate limits, which keeps it from a 5.

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?

Well front-loaded and sectioned with headers (WHEN TO USE, RETURNS, dataset types, EXAMPLE), so an agent can scan it quickly. It is long and the two worked examples border on redundant with the schema, but every section carries substantive information.

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 complex, nested-filter export tool with no annotations and no output schema, the description covers the return shape (data, metadata fields, suggested_next_queries), the pagination contract, and per-dataset behavior. Nothing essential to correct invocation is missing.

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 100%, so the baseline is 3, but the description adds real meaning: it explains the dataset-type enum values, clarifies that filters combine time/geo/venue_type/observation_family, and describes cursor as reading the next page with the same dataset and filters. This goes beyond restating the schema.

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 (export) and resource (observation data as a structured dataset) and enumerates the four dataset types it can produce, letting an agent separate it from read/query siblings like query_observations or get_dataset_stats. It also pins down scope with pagination limits and ordering, so the tool's role is unambiguous.

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 explicit 'WHEN TO USE' block gives four concrete scenarios (external analysis, ML/reporting datasets, structured vehicle/commerce data, cross-signal correlation). It stops short of naming alternatives or exclusions (e.g. when to query_observations instead), but the positive usage context is clear and actionable.

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