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

Annotations already declare idempotentHint, destructiveHint=false, and openWorldHint=false. The description adds valuable behavior not in the annotations: the dedup_key mechanism for idempotency and the explicit 'never sends anything' guarantee, which prevents an agent from mistaking this for an outreach action. It omits permission requirements and whether records can be modified later.

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 compact sentences, front-loaded with the core action, followed by the idempotency instruction and the no-send guarantee. No filler; every sentence carries useful information.

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?

An output schema exists, so return-value explanation is not required. However, for a write tool with a deeply nested, 0%-documented input object and multiple enums, the description covers only the high-level payload concepts. It does not clarify how to link the touch to a relationship/company, what provenance values mean, or which fields are effectively required within the touch object.

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%, so the description must carry parameter meaning. It explains the event payload conceptually (dated event, provenance, evidence, dedup key) but leaves many nested fields — relationshipId, occurredAt vs createdAt, actorUserId, agentName, summary, priorValue/newValue, and most enum values — undocumented. It also uses 'dedup_key' while the schema field is 'dedupKey'.

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 — 'Records one dated event on a relationship' — and enumerates concrete event kinds (intro, email, meeting, call, document request, reschedule, note, draft sent). This clearly distinguishes it from read siblings like fundraising_get_list_touches and from outbound tools like fundraising_send_chat_reply.

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?

The description gives clear usage context: record one event with provenance/evidence and pass a stable dedup_key so repeated checks do not duplicate. It also clarifies 'This never sends anything,' which helps an agent choose it over outreach tools. It does not name specific alternative siblings or exclusions, so it falls short of a 5.

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