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

Annotations already declare readOnlyHint, destructiveHint=false and openWorldHint, so safety is covered; the description goes further by disclosing the output ordering (est_clicks_lost) and the epistemic limitation that GSC and SERP tools cannot actually observe AI Overviews. It also enumerates competing explanations (Featured Snippet, Map Pack, ads, weak title/snippet, brand queries), which is behaviorally useful. It stops short of describing pagination or truncation behavior at row_limit.

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 core definition is front-loaded in the first sentence, followed by qualification logic, then caveats and a next step. Density is high but every clause carries operational meaning — no filler or restatement of the title.

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?

With an output schema present, the description does not need to explain return shapes, and it uses that space instead for the heuristic, its failure modes, and the verification path. For a 9-parameter diagnostic tool that is explicitly a heuristic, nothing an agent needs to call or interpret it correctly 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 only 56%, and several thresholds (max_position, max_position_change, min_impressions, min_ctr_drop) have no schema descriptions at all, so this text carries real weight. It supplies the actual qualification rule across both windows, including the non-obvious detail that baseline requires only half of min_impressions, and explains that min_ctr_drop is a fraction (0.30 = 30%) and that exclude_terms are case-insensitive substrings for brand words.

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 opens with a specific, testable definition: queries whose CTR fell while position held, framed as the footprint of an AI Overview or answer box. That verb+resource+signal combination is distinct from siblings like find_content_decay or find_quick_wins, so an agent can route without opening a schema.

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?

It clearly states when results apply (CTR drop with stable position) and prescribes a verification workflow: check a few rows with serp_top_results before acting, and label output as a suspicion rather than a measurement. It does not explicitly say when to choose find_content_decay or find_quick_wins instead, which is the main gap for a diagnostic tool with many analytics siblings.

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