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

Annotations declare a destructive, non-idempotent write, and the description adds substantial context beyond that: GTM PUT is a full replace, so the current object is fetched, the given fields applied, then written back with fingerprint preserved, and unlisted parameters are retained unless replace_parameters=true. The preview/apply gate via `confirm` further discloses the safety model.

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?

Dense and front-loaded, starting with the verb and entity kinds, then per-parameter semantics, then safety. It is long and uses telegraphic fragments, but nearly every clause adds operative detail (e.g., the eventName example, the removal case) rather than filler.

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?

An output schema exists so return values need not be explained, and the description covers the non-obvious mutation mechanics an agent must know: partial-update behavior, full-replace preservation, and the confirm gate. Nothing needed to invoke correctly 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 description coverage is 0%, so the description must carry the burden and does: kind enum values, path source, name as rename, firing_trigger_ids as comma-separated with empty = keep, parameters format (JSON object or GTM parameter list, with a worked table/list example), replace_parameters semantics, and confirm behavior. All seven parameters are meaningfully explained.

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?

Opens with a specific verb+resource ('EDITS an existing GTM tag/trigger/variable/workspace') and scopes it to the four GTM entity kinds. It also names the sibling list tools (list_gtm_tags/triggers/variables/workspaces) that supply the required `path`, so an agent can distinguish this from create_gtm_tag, delete_gtm_entity, etc.

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?

Gives clear operational context: 'Provide only what changes', confirm=false previews vs confirm=true applies, and replace_parameters is 'needed only to REMOVE a parameter'. It does not explicitly route to create/delete siblings for the non-edit cases, so it stops short of full when/when-not routing.

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