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

Goes well beyond the annotations by disclosing the side effect on last_contacted_at, that it writes only the caller's own contact book, that it executes immediately rather than returning a plan_token, and that it is reversible from the same surface. This contrasts the tool against the class of destructive/outbound/financial actions that do propose and wait, which is exactly the behavioral context an agent needs.

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?

Purpose and the kind taxonomy are front-loaded, and every clause about occurred_at, source, and undo earns its place. The capitalized CONFIRMATION paragraph is longer than strictly necessary for a tool call, but it carries non-obvious policy the agent cannot get elsewhere.

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 mutation with no output schema and zero schema descriptions, the definition covers what is written, side effects, defaults, format constraints, the undo path, and the execution model. An agent could call this correctly without opening any other field.

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 0%, so the description must carry the load and largely does: it explains the semantic difference between the two enum groups for 'kind', the requirement of 'text' for note/fact, defaults and format for 'occurred_at' (ISO, default now, no future dates), and the default value for 'source'. Only 'source_ref' and 'contact_id' are named without explanation, a minor residual gap.

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 precise verb and resource — 'Add a dated entry to a person's timeline in the caller's OWN contact book' — and immediately enumerates the entry kinds, so the agent knows exactly what gets created and where. It also distinguishes itself from create_event for planned meetings, which is concrete sibling differentiation.

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 explicit when-to-use split between interaction kinds (meeting/call/message/email move last_contacted_at) and note/fact (something learned, requires 'text'), plus a hard negative ('not in the future — a planned meeting is create_event') and a named undo path (delete_person_interaction).

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