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

Far beyond the annotations: it explains that empty/omitted values are no-ops recorded in 'ignored_empty', that field removal requires an explicit clear list, that required fields are not clearable (not_clearable) and can only be replaced, and that conflicting set+clear returns conflicting_fields. The MCC→direct-access scenario with its USER_PERMISSION_DENIED pitfall is exactly the kind of context an agent needs before a destructive change. Consistent with destructiveHint=true.

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?

Front-loaded with purpose, then progressively details the clear semantics and error cases; every block carries real information. It is long, and the clear/ignored_empty rules could be tightened slightly, but nothing is 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?

For a destructive 4-parameter nested-object tool, everything an agent must know to call it correctly is present: per-source fields, clear-vs-set interplay, required-field constraints, permission errors and response keys (updated/cleared/ignored_empty). The output schema exists, and the description does not waste space re-explaining return shapes.

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 0%, and the description fully compensates: it defines the source enum, the exact id fields per source (google_ads {customer_id, login_customer_id?} etc.), the clear[] semantics with a working example, and that workspace is an optional slug when only one workspace exists. Each of the 4 parameters is covered with meaning the schema cannot provide.

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?

Specific verb+resource: 'Source-IDs eines Workspace setzen — ersetzt den Portal-Roundtrip beim Onboarding'. It even frames the concrete use case (linking a freshly created GTM container). The enumerated source list makes the affected domain unambiguous.

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?

Use case is stated explicitly (onboarding, skipping the portal roundtrip) and permission scoping is spelled out (owners/admins only, member_restricted, source_not_enabled). It never names a sibling alternative (e.g. list_workspaces to obtain the workspace slug), which keeps it below a 5.

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