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

Goes beyond annotations by disclosing the side effect that a new contact is created when no match is found, that "phone alone is enough" to identify someone, and that outcome drives a downstream write (appointment vs. call-back task). It doesn't say what happens on repeat calls with the same number (duplicate risk), which matters for a non-idempotent write.

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?

Three tightly packed sentences, front-loaded with the verb and resource, then identity logic, then the outcome branch mapping. Dense but no filler; the example sentence earns its place by anchoring the phrasing.

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 13-parameter mutation tool with no output schema and sparse schema descriptions, the description covers the decision-critical flow (who is this, what happened, what gets written). Gaps remain around return value, defaults for kind/time_zone/booking_minutes, and duplicate handling on re-log.

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 only 15%, so the description must carry the load. It does explain the highest-value coupling — outcome "booked" pairs with booking_starts_at and "follow_up" pairs with follow_up_date, and phone/email/contact_id act as alternative identity keys — but kind, time_zone, booking_minutes, name, note, and user_goal get no mention.

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?

Specific verb and resource ("Record a phone call or walk-in the owner just had") plus the full one-step behavior: identity resolution by phone/email/contact_id, contact creation, then one of three outcome branches. This clearly separates it from siblings like upsert_contacts, book_callback_slot, and manage_appointments.

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 a concrete usage example ("log a call from Mike, 555-0142, call back Thursday") and an explicit self-service constraint ("Resolve relative days to a date yourself"). It doesn't name alternative tools for the create-only or appointment-only cases, so the when-not-to-use side is implied rather than stated.

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