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

Adds real behavioral context beyond annotations: the grant is single-use with a 10-minute lifetime, scoped to a bounded whitelisted query, and crucially that no rows come back in the MCP response. This is important for an agent not to expect inline data. It does not, however, state auth/permission requirements or what happens on an expired/reused grant.

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, front-loaded with the core action and artifact, and the response-shape caveat placed last. No filler.

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 usefully states the return is a URL and not rows, and annotations are consistent (readOnlyHint=false matches a persisting grant). But the low parameter coverage and absence of auth/expiry-edge details leave meaningful gaps for a query tool with 6 params.

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 only 17% (just customer_id documented), and 6 parameters exist. 'Bounded' faintly hints at the limit cap and 'whitelisted' at the family enum-like constraint, but family, date_from, date_to, limit, and connection_context receive no meaning in the description, so the large coverage gap is not compensated.

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?

States specific verbs (persist, return) and the concrete artifact (a single-use download grant / CSV export URL) for a bounded whitelisted deep-analysis query. It is clear what the tool does, but it never names google_ads_deep_analysis_query, the obvious sibling it differs from, so an agent must infer the export-vs-inline distinction.

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?

No explicit when-to-use or when-not-to-use guidance. The presence of google_ads_deep_analysis_query suggests this is the export path for the same query family, but the description never says to pick this one when you want a file rather than rows. Usage is only implied.

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