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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=true, so the safety profile is covered and the description need not restate it. What the description adds is a conceptual definition of the filter logic (high impressions + low CTR + page 1-2), which helps the agent trust the result set. It does not disclose the default date window, default row limit, or how thresholds default, which are meaningful behavioral traits for a data-query tool.

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 front-loaded sentence with zero filler; the scoping criteria come first and the actionable interpretation is parenthesized at the end. Nothing can be removed without losing meaning.

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 an 8-parameter analytics tool with no schema descriptions, the description is under-specified. Most importantly, it never indicates the time window analysed when start_date/end_date are left null, so the agent cannot reason about what period the 'quick wins' reflect, nor what row_limit does to results. The existence of an output schema relieves it of explaining return values, but the input-side gaps remain substantial.

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% across 8 parameters, so the description carries the full burden and only partially meets it. It conceptually maps to max_ctr ('low CTR'), min_impressions ('high impressions'), and the position bounds ('page 1-2'), but leaves site_url, start_date, end_date, and row_limit completely undefined, and gives no units (CTR as a 0-1 fraction) or defaults. The page-vs-position mapping is also loose relative to the actual min_position=5/max_position=20 defaults.

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 verb (find) and a precisely bounded resource: queries sitting in positions corresponding to pages 1-2 with high impressions but low CTR. The parenthetical '(snippet/title fix candidates)' states the actionable outcome, which separates it from diagnostic siblings like find_content_decay or find_cannibalization. It stops short of naming an explicit sibling alternative, so it is a 4 rather than a 5.

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 implied rather than stated: the phrase 'snippet/title fix candidates' tells the agent this is for identifying metadata-rewrite opportunities, but there is no explicit when-to-use/when-not framing. No alternative sibling (e.g. find_content_decay, find_cannibalization, get_search_by_page_query) is mentioned for adjacent intents. The agent can infer intent but must guess at boundaries.

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