send_push_notification

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

Strong disclosure beyond the annotations: no queue insert, no delivery, and a stated prerequisite. Slight tension with the structured hints (readOnlyHint=false and the '[Write]' label) since the description says no write actually occurs, but the description is clarifying behavior rather than contradicting it outright.

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?

Two terse sentences, front-loaded with the unsupported status, and the write marker at the end. Minimal waste; the '[Write]' tag is a useful scannable signal rather than 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 disabled stub the description covers the essential 'do not rely on this' message, but it omits the single most actionable piece of context: which tool to use instead. With no output schema, that routing information is the main remaining gap.

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?

All 5 parameters have 100% schema description coverage (title, body, user, group, action_url), so the schema carries the semantics. The description adds nothing about parameter meaning, which is acceptable at this coverage level but not additive.

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 names the resource (push delivery) and immediately states the defining fact: it is UNSUPPORTED and performs no queue insert or delivery. This distinguishes it from a working notification tool, though it never says what the tool would send or to whom beyond the 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?

It gives a prerequisite signal ('requires a validated notification workflow'), which tells the agent the tool cannot be used standalone, but it names no concrete alternative despite siblings such as schedule_notification, create_notification, and send_emergency_broadcast existing. Usage is implied rather than directed.

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