ad_manager_google_get_conversions

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

Annotations already declare readOnlyHint=true, destructiveHint=false, and idempotentHint=true, so the safety profile is covered. However, the description adds no additional behavioral context such as return format, pagination, filtering behavior, or side effects. The description does not contradict annotations (annotation_contradiction=false), but it contributes nothing beyond the structured metadata.

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 extremely concise ('Get conversions'), but it is under-specified rather than efficiently structured. It front-loads nothing useful and lacks any elaboration. While brevity is good, a two-word description provides no structural value; it is closer to a tautology than a helpful summary. It does not earn its place because it adds almost no information beyond the tool name.

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 6 parameters, no output schema, and a complex domain (ad manager with many siblings), this description is severely incomplete. There is no mention of required vs optional parameters, default behavior (e.g., locationId defaults to GHL_LOCATION_ID), what data is returned, or how it relates to other conversion-related tools. An agent cannot reliably determine scope, constraints, or expected outcomes from this description alone.

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?

The input schema provides descriptions for all 6 parameters (100% coverage), so the baseline for schema coverage is 3. The description itself does not add any parameter semantics—it does not mention filters, date ranges, types, or defaults. Since the schema already covers each parameter clearly, the description adds no extra meaning but is not penalized heavily because the schema is self-explanatory.

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 'Get conversions' is a very generic verb+resource statement but lacks specificity. It does not specify what kind of conversions (ad conversions, conversion goals, etc.), which platform (Google is implied by the name but not stated), or how it differs from siblings like ad_manager_google_get_conversion_by_id or ad_manager_google_get_conversion_goals. It is not a tautology but is minimally informative and fails to distinguish the tool within its context.

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?

There is no guidance on when to use this tool versus alternatives. The description provides no context about prerequisites, intended scenarios, or exclusions. Sibling tools with similar names (e.g., get_conversion_by_id, get_conversion_goals) are not mentioned, leaving the agent to infer usage without any support.

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