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

Annotations already declare non-read-only, open-world, non-idempotent, non-destructive, so the safety profile is covered. The description adds real context beyond them: sending is gated by lease ownership ('Only the cable that holds the lease sends'), the message is stamped with cable and epoch, and the send is recorded to the line's memory — all behavioral facts the annotations do not carry.

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 core action and compressed into a single dense sentence with no filler. The domain vocabulary ('cable', 'epoch', 'the memory of the line') makes it harder to parse on first read than a plainer phrasing would, costing it the top mark.

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 13-parameter, all-optional tool with no output schema, the description covers the essential question — how the destination account is chosen — and the privilege model for sending. Remaining gaps are the relationship to the overlapping siblings (line_edit, line_react) and which parameter combinations are valid, which are only implicit in the schema.

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%, so a baseline of 3 would be defensible. The description goes further by articulating the precedence chain among the mutually optional addressing parameters (reply_to > account > kind defaults), which the per-parameter schema text does not state as a combined rule for a tool with zero required parameters.

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 message as the line') plus the scope of channels it can route through (Telegram bot, Gmail, wired accounts). However, it never distinguishes itself from the sibling tools line_edit, line_react, and line_inbox, which overlap with the 'edit', 'react_to', and 'reply_to' parameters documented in this schema — an agent has no signal about which entry point to prefer.

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 a clear resolution order for the addressing parameters: 'reply_to answers through the same account and thread, account picks an account, kind uses the default outgoing account of that kind.' That is genuine when-to-use-which guidance. It stops short of exclusions, e.g. it does not tell the agent when to call line_edit or line_react instead of using the built-in edit/react_to parameters.

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