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

Annotations only declare the generic write profile (readOnlyHint=false, destructiveHint=false, non-idempotent, closed-world); the description goes well beyond that by disclosing the consent policy, what "draft" and "send" produce, and that sends are labelled as agent-authored. It does not address reversibility or rate/duplication behavior, and the 'draft'/'send'/'off' values do not appear anywhere in the schema.

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 with the action and its effect, then usage, then consent — a sensible order with no filler sentences. The em-dash-heavy packing makes the middle sentence dense, but nothing is redundant.

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?

With only two required string params, an output schema handling returns, and consent/delivery behavior explained, an agent has what it needs to invoke this correctly. The one gap is that the consent mode referenced ('draft'/'send'/'off') has no corresponding parameter, leaving it unclear how the caller selects a mode.

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 100% and the schema already documents both "to" and "what" with its own example, so the description adds no syntax or format detail beyond it. The inline example ("promenad i kväll?") duplicates the schema's example rather than extending it.

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 ("Send a light pling to a friend — a tiny nudge") and explains the delivery mechanism (a message in their 1:1 chat). It also positions itself against heavier siblings by calling itself "the lightest way to get two people to meet," so an agent can distinguish it from send_message or suggest_dinner.

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?

Gives an explicit trigger ("offer it when the person misses someone or the feed has ended") and an explicit constraint ("Only when the person wants it"), which is real when-to-use guidance. It stops short of naming an alternative tool for the heavier cases, so routing is implied rather than spelled out.

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