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

Annotations already declare this is a safe read, but the description adds material behavioral facts: hits are static JSON/CEL scans of specific fields rather than live BigQuery, an empty result is success/safe-to-delete, and results are capped at 100 with a truncated flag.

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?

Purpose and scoping are front-loaded, and every clause carries information (semantics, caveats, cap). It is dense with em-dash asides rather than wasteful, though slightly packed for a single paragraph.

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?

No output schema exists, yet the description pre-empts the questions an agent would have about results: what empty means, what is scanned, and the truncation behavior. Nothing needed to call it correctly or interpret the response is missing.

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% and the schema already documents the id-wins rule, but the description adds non-schema meaning: 'Native cos_* names work with name alone,' clarifying the name parameter's accepted domain.

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 a specific verb and resource ('List stored objects that reference a label dimension column') and enumerates the object types, so an agent distinguishes it from list_label_dimensions (which returns dimensions, not usages) without opening either schema.

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?

Explicitly frames the use case ('before rename or delete') and names the complementary tool to source ids from ('Pass id (from list_label_dimensions)'). The condition that selects the parameter path is spelled out, leaving nothing to inference.

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