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

Annotations already mark the tool as read-only and idempotent, and the description adds substantial behavioral context beyond that: it explains the 2–3 day data lag, that keywords without history are omitted, that position is null when a window has no impressions, that by_page is computed before the top cut, and that it surfaces a 'not connected' state instead of silently returning empty rows. This is exactly the kind of non-obvious behavior an agent needs.

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?

The description is long but information-dense, with every sentence contributing a distinct fact: comparison windows, metrics, grouping, sorting, defaults, country handling, data lag, exclusions, and error behavior. It is front-loaded with the core purpose before covering parameter behavior and use boundaries.

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?

Given the tool's moderate complexity, the presence of an output schema, and rich annotations, the description covers all expected context: window semantics, defaults, exclusions, data freshness, edge cases for missing impressions, and alternative tools. An agent can select and invoke this tool correctly without additional documentation.

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?

Although the schema has 100% parameter description coverage, the tool description adds operational meaning beyond the schema: sort options map to concrete meanings, default country behavior falls back to each keyword's snapshot country, by_page is applied before the top cut, and keyword_ids max 200 can be omitted to include all tracked keywords. These details are not inferable from the schema alone.

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 names a specific resource (Google Search Console keyword trends) and a precise operation: comparing the last window_days against the prior window_days with per-keyword metrics and deltas. It also explicitly contrasts itself with get_keyword_rankings and list_keywords, so it is clearly distinguishable from siblings.

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 gives explicit when-to-use guidance ('answers which pages are losing traffic') and provides direct exclusions with named alternatives: 'Not for the current position or ctr (use get_keyword_rankings) nor volume and difficulty (use list_keywords).' It also clarifies the sync cadence and the Search Console connection failure behavior, leaving little ambiguity about when to invoke this tool.

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