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

The description adds substantive policy context beyond the annotations: approval must happen in GenAds, chat messages never constitute approval, and the affected-plan count is project-scoped while other advertiser campaigns may still depend on the audience — a useful blast-radius warning. What it omits is any reconciliation with the supplied annotations, which declare readOnlyHint=false and destructiveHint=true; a tool described only as 'Read' leaves the agent unaware that the call is non-read-only and destructive.

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 sentences, front-loaded with the purpose followed by the approval constraint and the scoping caveat; there is no filler. It is slightly telegraphic — phrases like 'capability qualification' are never unpacked — but nothing is redundant.

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. But for a high-complexity call with a five-field work-session envelope (work_id, request_key, read_skills, expected_catalog_version, plan_id), the description says nothing about the session protocol, what the returned review contains, or what a non-approved state looks like, leaving the agent dependent on partial schema descriptions.

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 only 50% across 6 parameters, and the description mentions none of them — work_id, arguments.plan_id, and request_key are documented nowhere. For a nested envelope requiring work_id, request_key, read_skills, and expected_catalog_version, the description should compensate for the coverage gap but adds zero parameter meaning.

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 plus a compound resource: 'Read the exact audience review, saved human approval and capability qualification.' That is more informative than the title restatement and tells an agent it is retrieving an approval/qualification artifact rather than a plan. It stops short of naming a sibling, so the boundary with genads_audience_plans, genads_read_audiences, or genads_audience_change must be inferred.

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 human must approve in GenAds' and 'Never infer approval from a chat message or create it yourself' give a real prohibition and imply the tool is the gate before an audience change. However, no alternative is named and there is no explicit statement of when in the workflow to call it versus the audience-plan or audience-read siblings, leaving the routing to inference.

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