site_snapshot

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

With no annotations provided, the description carries the full disclosure burden and handles it exceptionally. It discloses that analysis must be grounded only in returned data, that speculation about causes is prohibited, that results must be rendered as dashboard-style interactive artifacts, and most valuably, that the position metric is an impression-weighted average over sparse deep-position data that should be treated as directional. These traits materially shape how an agent interprets and reports results in ways annotations never could.

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 (~200 words) but deliberately structured with labeled sections (IMPORTANT, PRESENTATION, POSITION) and the core purpose is front-loaded in the first two sentences. Every section serves a purpose, though there is some redundancy among the three analysis rules (only use returned data / do not speculate / say when data is insufficient), and the presentation requirements could be tightened 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 a low-complexity tool (one optional parameter, no output schema, no annotations), the description covers what data is returned, how to analyze it, how to present it, and how to interpret the trickiest metric (position). The main gaps are the exact raw response format and the categorization implied by 'tabbed sections,' but nothing required to call the tool 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 100% ('Number of days per period'), so the baseline is 3. The description adds value by clarifying that the tool makes a comparison 'to the prior period,' implying the days parameter defines two equal-length windows (current vs. prior), which is meaning beyond the raw schema. It does not, however, add bounds, valid-range guidance, or consequences of extreme values for the parameter.

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 first sentence uses a specific verb and resource ('Get a quick overview of how the site is performing') and enumerates the exact returned metrics (total clicks, impressions, CTR, position) plus the prior-period comparison. This makes it distinguishable from most siblings as the general snapshot tool versus specialized diagnostics like traffic_drops or ctr_opportunities. However, it never explicitly names a sibling or states what the tool is not, so differentiation from a tool like multi_site_dashboard or advanced_search_analytics is implicit rather than explicit.

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 context is only implied by the phrase 'quick overview' — suggesting a high-level performance check rather than a deep-dive diagnostic. There is no explicit when-to-use guidance, no exclusions, and no mention that specialized questions (traffic drops, content gaps, cannibalization) belong to sibling tools. The extensive IMPORTANT/PRESENTATION/POSITION blocks govern post-call analysis and interpretation, not tool selection.

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