gtm_find_references

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

With no annotations provided, the description carries the full behavioral burden. It explains the lack of referential integrity and the silent-breakage consequences, which is valuable context for why the tool should be used. It doesn't explicitly state that it is read-only or describe return shape, but 'Find' and the preflight framing make the non-mutating intent 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 compact and front-loaded: one sentence states the function, and a short follow-up explains when and why to use it. Every sentence adds value, and the example of {{Name}} interpolation makes the risk concrete without bloat.

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 read-only lookup tool with an output schema handled separately, the description covers the key operational context: what it searches for, when to run it, and why it matters. It doesn't detail how to scope by container or workspace, but the core agent decision—use this before destructive changes—is fully supported.

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 must compensate. It adds the important clarification that matches can be 'by name or id', which the schema field 'entity_name' alone doesn't convey. However, the other parameters (account_id, container_id, workspace_id) are not explained at all, leaving the scoping semantics ambiguous.

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 object: 'Find everything that references a variable or trigger, by name or id.' This clearly identifies the operation and distinguishes it from other GTM tools like gtm_get_entity or gtm_audit_container, which do different things.

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 directive 'Run this before deleting or renaming' gives an explicit usage context and tells the agent when the tool is the right choice. It doesn't list alternative tools or exclusion cases, but the preflight purpose is strong and actionable.

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