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

Annotations already declare the mutation profile (readOnlyHint=false, destructiveHint=true, openWorldHint=true); the description adds genuinely new behavior — that the write produces a journal entry, and that workspace is optional when only one workspace exists. It does not clarify reversibility or error behavior for an already-matching status, so it stops short of a 5. No contradiction with destructiveHint, since pausing is the intended state change.

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?

Four short, front-loaded sentences: action and allowed values first, then the sibling alternative, then the workspace nuance. Dense but every sentence carries information; only the workspace caveat is slightly tacked on at the end.

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 described, and the side-effect and status-value gaps are covered. However, for a 3-required-parameter mutation with zero schema documentation, the description never says where ad_group_id and criterion_id come from, leaving the agent to guess at identifier sourcing.

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%, and the description compensates for only half the parameters: it defines the valid status strings (ENABLED/PAUSED, which the schema leaves as a bare string with no enum) and explains the workspace slug/null behavior. ad_group_id and criterion_id — the two identifiers an agent most plausibly gets wrong — are left unexplained, with no hint that criterion_id comes from ads_list_keywords.

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 states a concrete verb pair and resource ("Keyword aktivieren oder pausieren"), gives the exact allowed status values, and explicitly distinguishes itself from the batch sibling ads_bulk_update_keyword_status. An agent can identify the operation without inspecting the schema.

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?

It names the alternative tool and the condition that selects it (multiple keywords in the same ad group → use the bulk variant, one API call and one journal entry instead of N). That is a clear routing rule, though there is no explicit "when not to use" (e.g., use ads_remove_keyword for deletion, or verify current status first).

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