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

The description adds useful context beyond the read-only/idempotent annotations: the data is 'indexed database samples' rather than live results, and 'absent observations are unknown' rather than zeroes. That provenance caveat is exactly the kind of behavioral nuance annotations cannot convey, though pagination behavior is not described.

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 dense sentences with zero waste and the key data-provenance caveat front-loaded. Nothing in the description is filler.

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 seven-parameter query tool with no output schema and low schema description coverage, the description leaves major gaps: return shape, snapshot granularity, direction meaning, and how filters combine. The provenance caveat is useful but not enough to make the tool fully callable with confidence.

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%, so the description needs to compensate, but it explains only URL and market implicitly. It does not explain the critical 'direction' enum (in/out/both), the 'area' enum (SEO/GEO/both), or how 'days', 'limit', and 'offset' shape the query.

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 resource: saved keyword positions by snapshot, URL and market. It distinguishes the tool from live rank tracking with 'not a live rank campaign', which helps separate it from read_live_search_campaign, though it does not explicitly name that sibling.

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 phrase 'not a live rank campaign' implies this is for historical saved data rather than live campaign data, but it never names an alternative tool or gives an explicit condition for choosing one over the other. Usage is inferred rather than stated.

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