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

With no annotations provided, the description carries the behavioral disclosure burden and does so well by disclosing key traits: single-use, 10-minute expiration, CSV export URL, bounded/whitelisted query scope, and no rows in the MCP response. It leaves some ambiguity around the whitelisting mechanism and URL usage but is substantially more transparent than a minimal description.

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?

Two dense sentences with no filler. The core behavior is front-loaded, and the key exclusion ('No rows are returned') appears immediately after the main action.

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 tool with five parameters, no output schema, and no annotations, the description is too thin. It does not explain what 'family' means, how date_from/date_to should be formatted, how the URL is returned or consumed, or how this relates to google_ads_deep_analysis_query.

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 only 20% (only customer_id is described), but the description does not explain family, date_from, date_to, or limit. The 'bounded whitelisted' phrasing gives indirect context but does not compensate for the missing parameter semantics.

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 and resource: 'Create a single-use 10-minute CSV export URL.' It also clarifies the scope ('bounded whitelisted deep-analysis query') and explicitly distinguishes itself from a row-returning query tool by noting 'No rows are returned in the MCP response.'

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 description gives a clear context for when to use this tool: when a CSV export URL is needed rather than inline query results. The 'No rows are returned' clause is an explicit exclusion, though it does not name the alternative sibling tool (google_ads_deep_analysis_query) directly.

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