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

Annotations declare it is not read-only, not idempotent, and open-world, but the description adds security-critical context they cannot convey: the link expires (default one hour), anyone holding it controls the phone, and it must never be pasted into logs or shared chats. That is exactly the behavioral burden a link-minting tool needs to 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?

Two tight sentences: capability and expiry first, then the sharing warning. Every clause earns its place, though the opening phrase 'a link a human can open' is slightly wordier than needed.

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 two-parameter tool with no output schema, the description covers what is produced (a shareable link), its lifetime, and the security implications of the return value. Nothing an agent needs in order to call or handle the result 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?

Schema description coverage is 100%, and the schema documents both phone_id and expires_in including pattern, range, and default. The description merely restates the one-hour default expiry, adding no syntax or semantics beyond the schema, so the baseline 3 applies.

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 ('Create a link a human can open to watch and control the phone') plus the operational purpose (human-in-the-loop control). This clearly separates it from sibling tools like act and observe, which are agent-driven rather than human-driven.

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 concrete when-to-use context ('for example to sign in or solve a check') and an explicit sharing constraint ('share it only with your user'). It stops short of naming alternatives such as act or observe for cases where no human interaction is needed, so the routing guidance is clear but not exhaustive.

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