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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, openWorldHint=true), it discloses the actual side-effect chain: changes are not live until a version is created and published. It also names two concrete failure modes ('error custom_code_disabled' for jsm/cvt_ types, 'invalid_id' for non-numeric workspace_id) and the implicit-name-derivation behavior, which is exactly the kind of non-obvious conduct an agent cannot get from structured fields.

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 critical constraint (needs version+publish to go live) is front-loaded in the opening parenthetical, and each subsequent sentence adds distinct operational content. It is dense and mixes languages with the English schema, but there is no filler to cut.

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 an output schema present, return values need no explanation, and for a 5-parameter create tool the description covers defaults, ID format, error codes and the publish lifecycle. The main residual gap is the expected structure of `parameters` for non-default variable types, which an agent building a jsm/cvt_ variable would still have to guess.

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 and mostly discharges it: it explains the variable_type domain and its default ('v', with 'jsm' and 'cvt_…' restricted), that workspace_id must be purely numeric, that workspace is an optional customer slug when only one workspace exists, and that omitting parameters derives the data-layer key from name ('dlv - foo' → 'foo'). Only the required `name` field and the shape of `parameters` entries remain unexplained.

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 ('Neue GTM-Variable im Workspace anlegen') with the lifecycle scope ('erst nach Version+Publish live'). The resource is unmistakably distinct from sibling tools like gtm_create_tag, gtm_create_trigger and gtm_create_version, so an agent can route on name plus first line alone.

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 when this applies (creating a variable in an existing workspace) and gives a key prerequisite via the publish/version note, but it names no alternatives and never says explicitly when to prefer this over a different variable mechanism. Usage is inferable rather than specified.

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