reply_to_companion

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

With no annotations, the description carries the full behavioral burden. It conveys that the reply surfaces in the user's panel, but says nothing about threading behavior with inReplyTo, whether the thread gets marked addressed, delivery/notification semantics, or permissions.

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 tight sentences, each earning its place: the first front-loads the action and destination, the second enumerates the triggers. No filler or restatement of the name.

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 simple two-parameter tool with no output schema or annotations, this covers purpose and timing but omits important routing context — notably how it relates to mark_thread_addressed and add_thread_message, and what happens to the thread after replying.

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%, so the schema already documents 'body' (Markdown allowed) and 'inReplyTo' (id of the message being answered). The description adds no parameter-level detail beyond the schema, which is the expected baseline.

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 target (answer the person watching, in their panel), which is distinguishable from sibling reads like get_companion_messages and thread-oriented add_thread_message. It stops short of naming those siblings, but the action is unambiguous.

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 three concrete triggers: a companion message needs a response, a decision is needed before continuing, or something they asked about is finished. These are genuine when-to-use conditions, though no sibling alternative or exclusion is named.

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