GTM: Test workspace (quick preview)

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

Annotations already declare readOnlyHint=true and openWorldHint=true, and the description does not contradict them (nothing is created or published). Beyond annotations it adds real value: the exact return payload ('compilerError + number of tags/triggers/variables') and the follow-up behavior on failure ('searches for the cause itself (likelyCauses)'), which tells the agent the tool does diagnostic work rather than just failing.

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?

Consistent with the calibration scale, a definition whose structured fields already carry the semantics scores in the middle band here; the prose is efficient (three short sentences, front-loaded) but the 'likelyCauses' sentence is somewhat compressed.

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 carries the return contract and does it well: names the fields returned and the error-diagnostic path. What is missing is the scope of the trial compile itself — whether it evaluates every entity in the workspace, whether it is side-effect free, or any rate/time expectations for a large container.

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 100% and each of the three IDs is already documented in-schema, including provenance hints (gtm_list_accounts, gtm_list_workspaces). The description adds no additional parameter semantics, so the baseline 3 applies.

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 names a specific verb and resource ('compiles the workspace as a trial') and adds the key negative qualifiers 'without a version and without publishing anything', which distinguishes it from gtm_create_version/gtm_publish_version. It never explicitly contrasts itself with the closest sibling, gtm_validate_workspace, so an agent still has to infer the preview-vs-validate split.

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?

Usage is only implied: 'without publishing anything' signals this is a pre-publish check, but there is no explicit 'use this before X' or 'use gtm_validate_workspace when Y'. No prerequisites, no exclusions, no cost/latency guidance are stated.

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