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

Annotations already declare readOnly/idempotent/non-destructive, so the description correctly spends its budget elsewhere: it warns that saved inbox entries and provider acceptance do not prove phone display or reading, which frames how the returned data should be interpreted. 'Without repeating it' also clarifies no send is triggered. What it omits is anything about cursor-based paging or result size.

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 what is read, then the specific-send option, then the interpretation caveat, then the channel boundary. No filler, though the telegraphic phrasing makes the guidance slightly harder to parse than necessary.

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 read-only tool with no output schema, the description covers intent and interpretation caveats but says nothing about the shape of 'audience' and 'receipts' or how engagement_cursor drives paging. An agent can decide to call it but must guess at pagination 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?

Schema description coverage is 0%, so the description must carry parameter meaning and only does so for notification_campaign_id. engagement_filter's enum values and engagement_cursor's paging role are left entirely undocumented, and event_id is only implied by 'this event'.

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?

States a specific verb and resource: reading an event's current audience plus recent in-app engagement receipts. The closing line 'Email/SMS remain separate' scopes it away from the email/SMS announcement siblings, though it never names the analogous tools such as get_sms_announcement_audience.

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 a concrete selection rule: pass notification_campaign_id to inspect one specific send rather than repeating it. 'Email/SMS remain separate' acts as an explicit when-not boundary, but no alternative tool is named for those channels, so the routing is only half explicit.

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