Open a direct text and file sharing window

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

Goes well past the annotations by disclosing the human-in-the-loop approval model, encrypted host-candidate WebRTC with no relay or discovery, the 30-minute window expiry, the fact that contents and pairing secrets are never returned to the agent, and that received saves require a new output_dir plus an explicit Save click. It also notes what the existing pairing observes (IP addresses, timing, negotiation metadata).

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?

Five dense sentences, front-loaded with the core action and followed by behavior, then constraints. Every sentence adds information, but the middle clauses are packed and slightly run-on (IP/timing/negotiation metadata in the same breath as transport details).

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 six-parameter, no-output-schema interactive tool, the description covers what the agent needs: prerequisites, human approval, that no content or secrets come back, the expiry, and the output_dir requirement. Nothing essential to calling it correctly is missing.

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?

With only 50% schema description coverage, the description compensates well: it maps host preloading to input_paths/text_path (UTF-8 text file), explains output_dir must be new with an explicit Save, and ties the 30-minute default to ttl_minutes. The required role enum (host vs reader) is only implied through 'Host may preload' and 'Receive saves', never stated directly.

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: 'Open a visible local browser companion for abox.tools Share Text', then clarifies the peer-to-peer text/file handoff. It is readily distinguishable from the other session tools (camera_session, walkie_session, voice_oncall_session) which are audio/video oriented, though it never names them explicitly.

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 clear operating context: the person must click Start or Connect and approve each reader, and it 'Requires directly reachable peers and an active graphical desktop.' That effectively excludes headless/agent-only use, but no explicit alternative tool is named for cases where those prerequisites fail.

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