log_contact

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

Annotations establish it is a non-read-only but non-destructive, non-open-world write. The description adds meaningful behavioral context: it must reflect a real contact rather than a fabricated send, and follow-up dates use YYYY-MM-DD. It does not add auth or idempotency details, but the annotations already carry the safety profile.

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 compact sentences with no filler, and the core action plus the critical misuse warning are front-loaded. Every clause earns its place.

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?

Output schema and annotations cover return values and safety, so the description needn't explain those. It is still incomplete for a 6-param mutation tool: parameter meanings are unaddressed and sibling differentiation from record_appointment/complete_follow_up is ambiguous given the 'appointment' overlap.

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 0% across 6 parameters, so the description must compensate. It only specifies the format for follow_up_on (YYYY-MM-DD) and leaves profile_id, channel, outcome, notes, and occurred_on semantics entirely undocumented.

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+resource: 'Record an actual contact/reply/appointment'. The exclusion clause ('Never use this to pretend a draft was sent') sharply distinguishes it from the draft-related siblings, so an agent can separate this from draft_enquiry/get_email_draft without opening schemas.

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?

Provides an explicit negative usage rule ('Never use this to pretend a draft was sent'), which clearly routes the agent away from draft tools. However, it does not name the alternative tools or clarify when to prefer this over close siblings like record_appointment or complete_follow_up.

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