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

Annotations already declare readOnlyHint=false with destructiveHint=false, so the write-but-safe profile is covered. The description adds genuinely useful behavior beyond them: this registers an ongoing subscription that fires on every data change, not a single delivery. However, it omits what an agent most needs to know operationally — whether repeated calls create duplicate subscriptions, how the subscription is removed, and what happens on invalid chart/destination IDs.

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?

A single sentence that front-loads the action and trigger, with the optional immediate behavior trailing. Every clause carries information and 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 three-parameter tool with no output schema the core is present: purpose, prerequisites, and trigger semantics. What is missing is lifecycle information — idempotency of repeated subscriptions and how to stop one — which matters because this tool creates persistent behavior rather than a single side effect.

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 only 33% (send_now only), so the description must compensate, and it does partially by explaining that chart_id originates from create_living_chart and destination_id from add_destination — real meaning beyond the bare string/integer types. The phrase 'optionally once right now' describes send_now's effect but is ambiguous about the default being true, and no format detail is given for the IDs.

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?

Specific verb (send) plus resource (a chart) plus trigger condition (every time its data changes) plus an explicit optional immediate-send mode. It also ties the chart and destination to the sibling tools that produce those IDs, so the agent can distinguish this from one-shot generation tools.

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?

The description establishes the prerequisite workflow clearly: the chart must come from create_living_chart and the destination from add_destination, which tells the agent what must exist first. It stops short of stating when not to use it (e.g., for a one-off send without subscribing to changes) or naming an alternative tool for that case.

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