export_search_analytics

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

Beyond the annotations it discloses real behavior: auto-pagination, a 500,000-row ceiling, a default 100,000 safety cap, that a file is written to GSC_EXPORT_DIR (~/Documents/sam-gsc-exports) and that the return is path plus preview. Minor unresolved tension: readOnlyHint=true while the tool creates a file on disk, which an agent may want clarified, but it does not mutate the remote GSC data.

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?

A single dense lead sentence carries purpose, mechanism, limits and return value, followed by a compact per-argument list. Nothing is padded and the most decision-relevant facts come first.

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 nine-parameter export tool with an output schema, the description covers destination, caps, defaults and return shape well enough to call it correctly. The only material gap is how to construct the filters argument, which is left to guesswork.

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 0%, so the Args block carries the whole load and largely does: env-var default for site_url, a dimension syntax example, YYYY-MM-DD date format, the default/max for max_rows, and the search_type values (web, image, video, news, discover, googleNews) which are not enforced as an enum in the schema. The weak spot is 'filters: Optional AND filters', which never explains the accepted string/array/object shapes the schema allows.

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 and resource plus the output medium: 'Bulk-export Search Analytics rows ... to a CSV file on this computer and return its path plus a preview.' That clearly separates it from the sibling read tools (get_search_analytics, get_advanced_search_analytics) which return rows inline, though no sibling is named 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 only implied by the word 'Bulk-export' and the row caps; there is no explicit statement of when to pick this over get_search_analytics / get_advanced_search_analytics or when a CSV export is inappropriate. An agent can infer the split, but must do the inferring itself.

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