multi_site_dashboard

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered. The description adds genuine behavioral context — results are compared against a previous period and properties are flagged as dropping/growing — but says nothing about how many properties are returned at once, ordering, or what a 'flag' looks like in the response.

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 sentence with the multi-property scope front-loaded and no wasted words. The telegraphic style ('flagged dropping/growing') is terse to the point of being slightly clipped, but nothing is redundant.

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 no output schema, the description does double duty and only partially delivers: it lists the metrics and the dropping/growing flag concept, which is the minimum needed to interpret results, but omits any indication of response shape or per-property structure. Adequate for a 3-parameter read-only aggregation tool, but thin.

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 67%; drop_pct and properties are already documented in the schema. The description's 'vs previous period' implies the days window governs both the current and comparison ranges, which adds real meaning the bare 'Days' schema field lacks, but it never states this explicitly nor explains the 7–90 bounds.

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 states a specific verb+resource ('health check across many properties') and enumerates the metrics returned (clicks, impressions, CTR, position) plus the comparison and flagging behavior. 'Across many properties at once' implicitly separates it from single-property siblings like property_overview, 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?

The phrase 'health check across many properties at once' implies the usage context (multi-property triage), but there is no explicit when-to-use vs. when-not, and no pointer to alternatives such as property_overview, compare_periods, or traffic_drops for drilling into a single site or a specific anomaly.

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