zas_send_direct

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

With no annotations, the description carries the full burden and does it well: nothing is stored, there is a ten-minute receive window, the call blocks for roughly a minute, and it returns either a result or a job id for zas_jobs. It also discloses the agent-attribution mark the owner sees and warns to confirm before sending secrets. Error behavior and what happens if the owner never presses Receive are left unstated.

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 purpose and the transport model, then timing, then the return contract, then safety. Mostly earns its place, but the return behavior is stated twice ('returns a job id to check with zas_jobs' and 'Returns the transfer result, or a job id'), which is a small redundancy.

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?

No output schema and no annotations, yet the description covers return shape (result or job id), the follow-up tool, the blocking latency, the human-in-the-loop requirement, and the sensitive-data caution. An agent has everything needed to call this correctly and interpret the response.

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 both parameters are already documented, establishing a baseline of 3. The description adds modest meaning — 'any file this process can read' clarifies the path scope, and the channel must be in Directo mode — but nothing about path formats, size limits, or what happens if multiple channels exist.

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 file) plus the transport constraint: a live device-to-device transfer into a channel in Directo mode, with nothing stored. That distinguishes it from a stored-upload sibling in substance, though it never names zas_send_file or zas_send_direct_fallback as the alternatives.

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?

Prerequisites are clear (channel must be in Directo mode, owner must press Receive within ten minutes, the call blocks for about a minute). What's missing is routing guidance: no statement of when to use this versus zas_send_file or zas_send_direct_fallback if the owner is unreachable or the channel isn't in Directo mode.

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