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

With no annotations provided, the description carries the behavioral disclosure burden. It clearly explains what the tool returns per action, how the level parameter changes row granularity, and the key Google limitation that cost is not split by conversion action. It stops short of explicitly stating auth requirements or error behavior, but the read-oriented wording and return-column breakdown make the tool's behavior clear.

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 front-loaded with the core purpose and every sentence earns its place: user-intent triggers, returned fields, level semantics, the no-cost limitation, and the ID format. Despite its length, it is tightly structured and avoids redundant repetition of the schema.

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 no output schema and no annotations, the description is thorough: it defines the expected output columns, explains both levels, calls out the missing cost dimension, and directs users to the sibling tool for that data. No essential call-time ambiguity remains.

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 the baseline is 3, but the description adds meaningfully beyond the schema. It clarifies that ad_account_id is a bare 10-digit customer ID, that rows are ordered by all_conversions descending, that campaign_id forces campaign level, and why there is no spend/CPA column. This gives an agent practical calling context the schema alone does not.

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 uses a specific verb and resource, 'Break a Google Ads account's conversions down BY CONVERSION ACTION', and gives concrete examples (Purchase vs Lead vs Sign-up vs phone call). It also distinguishes itself from the lumped-total view and from adsap_google_get_insights by explicitly noting what it does not include.

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?

It explicitly states when to use the tool: when the user asks which conversions the account is getting, whether a specific action is firing, or why All conversions is far above Conversions. It also names the alternative tool for cost/CPA data, giving an agent clear selection criteria.

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