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

Annotations already mark readOnlyHint and destructiveHint false, but the description goes far beyond that: it specifies exactly which side effects are avoided, notes that provider calls and model tokens are still consumed, and discloses refusal behavior on paused plays. This is rich transparency for a dry-run tool.

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 dense but every sentence adds value, from the core 'no side effects' statement to the output details and cost disclosure. It is slightly long and packs many technical terms into a few sentences, but the structure is logical and front-loaded with the most important behavior.

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 does an excellent job of explaining what the tool returns: match count, 10-person sample, size.precision semantics, unmapped facets, unresolved values, alreadyALead flags, and account_list resolution. It also covers cost and refusal conditions, making it effectively complete for an agent deciding to call it.

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%, including detailed descriptions for every key enum value. The description adds context about output semantics (size.precision, unmapped, unresolved) but does not need to re-explain parameters. Baseline 3 is appropriate since the schema already carries the parameter meaning.

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 a specific verb and scope: 'Dry-run ONE lane' and contrasts it with a real run by listing what it does NOT do. It clearly distinguishes the tool from gtm_run_source and other siblings by framing it as a side-effect-free preview with a 10-person sample.

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 clearly implies when to use this tool: when you want to see what a run would keep without committing a lead, budget, or run clock. It does not explicitly name sibling alternatives like gtm_run_source, but the dry-run framing and 'what a run would keep' provide strong contextual guidance. The refusal on paused plays also gives a concrete exclusion.

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