get_field_metadata

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

Annotations already mark the tool read-only and open-world, and the description adds concrete behavioral context by specifying that the output is selectable, filterable, and sortable field metadata. It also discloses that customer_id falls back to a default when omitted. There is no contradiction with the annotations.

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 a single purpose sentence plus a compact Args block, with no filler or redundant restatement of the input schema. The primary purpose is front-loaded, and every line contributes meaningful information.

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 simple read-only two-parameter metadata tool, the description adequately covers purpose, parameter semantics, and default behavior. The absence of an output schema means the exact return shape is implied rather than explicit, but the description names the three field categories expected, which is sufficient for most usage.

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 0%, so the description carries the full burden for explaining parameters. It explains resource_type with three concrete GAQL examples ('campaign', 'ad_group', 'ad_group_ad') and notes customer_id's default behavior. However, customer_id is still only described as 'Customer ID' without any format, prefix, or validation details.

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 opens with 'Get selectable, filterable, and sortable fields for a GAQL resource' – a specific verb with a clear resource and result type. It distinguishes this tool from data-returning siblings like execute_gaql and list_gaql_resources by focusing on field metadata rather than query execution or resource enumeration.

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 implies the tool is used when preparing or understanding GAQL queries by exposing the resource's queryable fields. However, it never explicitly says when to prefer this tool over siblings such as list_gaql_resources or execute_gaql, nor does it provide any exclusions or decision rules.

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