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

Annotations declare destructiveHint=true and idempotentHint=true, so the description's key contribution is reframing that destructiveness: 'The previous row is kept in history' tells the agent the edit is recoverable, and 'nothing changes on the provider' scopes the blast radius to the local panel. It does not cover permissions or what happens if all fields are omitted.

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?

Three short sentences with the mutation tag '[write]' front-loaded, then the identifier/field mapping, then the behavioral caveats. No filler and nothing buried.

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?

No output schema exists, so the description should cover return behavior, and 'the previous row is kept in history' does hint at versioning; the panel-vs-provider distinction completes the picture. The remaining gap is the all-optional parameter set with no statement of failure behavior.

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?

With 0% schema description coverage, the description must carry the load, and it does: it identifies the two audience identifier forms (id or uuid), the three editable fields (title, notes, branch website), and the two website identifier forms. The one gap is that it never states that every parameter is optional or what an empty call does.

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 plus resource: 'Edit an audience's ... panel title, notes or branch website', with a clear scope qualifier ('Panel-only'). It does not name a sibling tool (e.g. sync_ads_audiences or delete_ads_audience), so differentiation comes only from the 'nothing changes on the provider' clause.

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 'Panel-only: nothing changes on the provider' line implies this is for local metadata edits rather than provider sync, which is useful routing context. However, it never explicitly states when to use this versus sync_ads_audiences or create_ads_campaign_from_audience, and there are no preconditions spelled out.

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