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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so safety is covered. The description adds genuinely new behavioral context: what fields a notification carries, that `get` surfaces CTA label plus link URL, that status may be omitted to list all, and what merge-tags are. It does not mention pagination behavior or result volume for `list`, which is the only remaining gap.

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?

Front-loaded one-line definition, then a schema of the object, then a bulleted action dispatch with per-action requirements. No sentence is redundant and the most decision-relevant information (event_id needed, action routing) appears early.

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?

Although an output schema exists (so return shapes needn't be explained), the description still supplies the domain vocabulary an agent needs to reason about results. Combined with 100% schema coverage and full annotations, nothing required to select an action or supply parameters correctly is missing.

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 coverage is 100%, so the baseline is 3; the description goes beyond by explaining the semantics of `status` values (published/draft/scheduled, omit for all), the purpose of `search`, the requirement of `notification_id` for `get`, and the origin of `event_id`. The `page` parameter is left to the schema, which is acceptable but prevents a 5.

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 ('Read push notifications ... for the provided event') and immediately defines the domain object (title, message text, optional CTA button). The `action` dispatch table makes clear this is the read-side counterpart to create_notification / delete_notification / publish_draft_notification, so an agent can distinguish it from siblings without opening a 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?

Each action is scoped with its own when-to-use condition: `list` for enumeration with optional status/search, `get` when the CTA text and URL are needed (requires notification_id), `list_template_tokens` when the agent needs merge-tags. It also routes the agent to search_events for the required event_id. It stops short of naming explicit exclusions (e.g., 'to create or modify notifications use create_notification / update_notification_schedule'), which keeps it at 4.

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