notification_request_send

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

Annotations are all false (readOnly, idempotent, etc.), so the description carries the disclosure burden. It explains the bounded-polling task behavior, the lack of upstream events, per-receiver failure reporting, and the requirement for MCP Tasks support—far beyond basic annotation info. No contradiction.

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?

Though long, every sentence earns its place: main action, task mechanics, prerequisites, completion behavior, client requirement, alternatives, cross-reference. It's dense and well-structured with no fluff, front-loading the core purpose.

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?

Given the tool's complexity (MCP task, failure handling, client constraints), this description covers all necessary context: what triggers, what it requires, what happens on completion, what to do without Tasks support, and which sibling to use for status. With no output schema, it even describes the return value.

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%: requestId is fully described with format and provenance. The description reinforces it ('Requires: notification_request_create -> requestId') but adds no new semantic meaning beyond the schema. Baseline 3 is appropriate.

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 opens with a specific verb and resource: 'Activates a notification request, triggering delivery to every added receiver.' It clearly distinguishes from siblings like notification_request_create (creates), notification_request_status (checks status), and notification_receiver_add (adds receivers).

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?

Explicit prerequisites are given (notification_request_create for requestId, notification_receiver_add for receivers). It also provides alternatives for clients without Tasks support (use autosend:true and poll status), and points to notification_request_status for progress checking. This is model usage guidance.

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