interest_over_time

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

With no annotations, the description carries the full behavioral burden and does disclose meaningful traits: results are downsampled to ~60 points, direction_now is a recent slope, direction may read as rising/new on stale peaks, and gprop channels have differing authority for answer engines. It still omits read-only/safety framing and any rate-limit or quota expectations for a Trends-backed call.

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 paragraph that front-loads what the tool returns and follows with parameter guidance; there is little waste. The embedded output-field inventory (mean, latest, peak, growth_3m/12m) is slightly list-heavy but each item is informative.

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?

An output schema exists, so the description did not need to enumerate return values, yet it does so usefully. For a 5-param, zero-coverage read tool with no annotations, the main remaining gaps are the semantics of geo, category, and timeframe, which an agent needs in order to call it correctly.

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 0%, so the description must compensate. It does well on two params (keywords bounded to 1-5, gprop values enumerated as ''/news/youtube/images/froogle with a rationale), but geo, category, and timeframe are never explained, leaving half the parameters semantically invisible to the agent.

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 verb+resource+scope: 'Search-interest time series (0-100) for 1-5 keywords'. It is easily distinguished from siblings like interest_by_region, trending_now, and compare_keywords because it explicitly frames the output as a per-keyword time series with direction metrics.

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 gives one concrete usage rule ('Use direction_now to decide whether to write about a topic *now*') and warns that 'direction can be rising or new for a topic that peaked months ago', which is a useful interpretive guardrail. However, it never says when to prefer this tool over compare_keywords or related_queries, so routing guidance is only implied.

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