Create Push Campaign

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

Annotations already declare the safety profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=false), so the bar is lower. The description adds genuinely non-obvious behavior: the campaign is only saved as a draft and cannot be sent or scheduled here, and audience targeting is a union across three id lists. It does not mention any permission/auth requirements or how duplicates across the id lists are resolved.

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 sentences, front-loaded with the core action and audience semantics, then the draft state, then the send/schedule limitation. Every sentence carries distinct information; there is no 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 mutation tool with 18 parameters, nested objects and no output schema, the description covers the lifecycle constraint (draft-only, no send) and audience resolution. It is slightly incomplete in that it never indicates what the call returns (e.g. whether an id is produced for later use), which matters because the description tells the agent the user must finish the workflow elsewhere.

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 67%, so the schema carries most of the load. The description adds real meaning for three parameters by defining the audience as a union of list_ids/tag_ids/segment_ids, which is not deducible from the individual schema entries. However, it says nothing about the other 15 parameters (priority, throttle_minutes, data_payload, action_buttons, etc.), so it does not fully compensate for the coverage gap.

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+resource ('create a push notification campaign') and immediately scopes it: the audience is the union of list_ids, tag_ids and segment_ids, and the result is saved as a draft. This distinguishes it from create-email-campaign/create-sms-campaign/create-in-app-campaign siblings without the agent opening any 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?

Explicitly routes the agent to list-lists for lists and list-tags for tags, and states that segments are managed in the Arsel dashboard. It also states a hard when-not: this server cannot send or schedule the campaign, so the user must do that from the dashboard — an unambiguous limitation no sibling could imply.

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