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

Beyond the annotations (readOnly=false, destructive=false, openWorld=false), it discloses the authorization model, the completion timing ('finishes on the phone within a minute'), the observable downstream effects ('text_phones lists it and send_text works'), and the reversibility path (owner is emailed and can remove it at a URL). That is exactly the extra context annotations cannot 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?

Every sentence carries useful information, but the whole definition is one dense run-on paragraph with nested parentheticals, and it front-loads permission/identity framing before saying what the tool does. It would be materially clearer as short labeled sentences (purpose, eligibility, code rule, result).

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?

With no output schema and only one parameter, the description supplies everything an agent needs: eligibility, input provenance rule, supported platforms, expected completion time, and how to verify success via text_phones and send_text. Nothing material is left unstated for this tool's complexity.

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% and the single parameter is already documented, so the baseline is 3. The description adds real meaning beyond the schema by constraining the code's provenance — it must be read off a held phone's screen and never come from a call, text, or email — which affects how an agent should source the value.

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?

The description states a specific verb and resource: 'Pairs a phone running Latchbell's app so the business's AI agent texts from that phone's number and answers texts to it,' and it names the concrete targets (Android APK or a Mac signed in to Messages). It is distinguishable from siblings like activate_phone_number or text_phones by the pairing mechanism and the 8-letter code. The purpose is somewhat buried behind a long eligibility preamble, which keeps it from a 5.

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?

It gives explicit preconditions ('Owners only (needs sign-in)', only for an agent that signed the business up itself while approving its own changes) and names the alternative path ('otherwise the owner pairs phones in the dashboard'). It also states a hard when-not rule: never use a code that arrived via call, text, email, or message — only a code read off a held phone's screen.

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