google_ads_auction_insights_analyze

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

The description is fully transparent despite no annotations. It states the tool is read-only, details the exact output structure including field names and value ranges (0-100 rounded to 1 decimal or None), specifies the thresholds for triggering insights (IS < 50/70%, rank-lost > 20%, etc.), and discloses an important limitation: Google Ads API v23 removed competitor-level data, so only impression-share proxies are returned. No contradictions with annotations (none provided).

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 thorough and well-structured. It starts with the core purpose, then details the output structure, then gives usage notes. It is slightly longer than necessary, but every sentence adds value. The front-loading of the main purpose is effective. A score of 4 reflects minor room for trimming without losing clarity.

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?

Given the tool has no output schema, the description fully describes the return format: fields like 'campaign_id', 'impression_share_metrics' with subfields, and 'insights' array. It also explains the logic behind insights firing conditions. The description covers all important aspects: purpose, parameters, output, limitations, and alternatives. No missing context for an analysis tool.

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%, so baseline is 3. However, the description adds significant value beyond the schema: for 'customer_id', it explains fallback to environment variables; for 'campaign_id', it tells how to obtain via another tool; for 'period', it provides usage recommendations (shorter for recent changes, longer for baselines) and lists all enum values. This elevates the score to 5.

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?

Description clearly states the tool's purpose: interpreting impression-share metrics and surfacing human-readable insights. It distinguishes itself from the sibling tool 'google_ads_auction_insights_get' by noting that this tool provides insights, while the sibling returns raw metrics. The specific verb 'Interpret' and resource 'campaign impression-share metrics' make the purpose highly specific and unambiguous.

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?

Explicit guidance on when to use this tool versus the alternative 'google_ads_auction_insights_get': 'For the raw metrics without insights use...' Additionally, it provides advice on period selection: 'Use a shorter window... when diagnosing recent changes; use LAST_90_DAYS for trend baselines.' This helps the agent decide on parameter values.

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