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

Annotations already declare write, non-destructive, non-idempotent, closed-world, so the description needn't restate safety. It instead adds genuinely non-obvious context: occurred_at reflects reality rather than entry time ('staleness math depends on the truth') and the summary's interpretive latitude vs. its factual provenance rule (CRM-10). It stops short of warning that retries will duplicate the record despite idempotentHint=false.

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?

The action and the critical occurred_at caveat are front-loaded, and every sentence carries substance. The trailing 'Effects: activity recorded.' is near-empty filler that adds nothing an agent doesn't already know from readOnlyHint=false.

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 6-parameter write tool with no output schema, the description covers the highest-risk semantic (occurred_at) well but leaves medium/direction undefined and never states what a successful call returns or how duplicates behave. Adequate but with clear omissions an agent would hit in practice.

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 67% and the description meaningfully enriches two key parameters beyond their schema text: occurred_at's distinction from entry time, and what belongs in summary (free interpretation, sourced facts). medium and direction still carry empty schema descriptions and no mention in the prose, leaving two enum parameters to inference.

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: 'Record a touch: what happened, when it actually happened, with whom,' which tells an agent this creates an activity record. It does not distinguish itself from nearby siblings like crm_add_event, crm_attend_event, or crm_draft_outcome, so an agent cannot route confidently on purpose alone.

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?

Usage is only implied by the action itself ('Record a touch'), with no explicit when/when-not guidance and no named alternative. Given the dense sibling set containing crm_add_event and crm_draft_outcome, the absence of routing guidance is a real gap.

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