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

Annotations already declare destructiveHint=false, readOnlyHint=false, openWorldHint=false, and the description adds real behavior beyond that: source text is NOT copied, only the caller's own note is, scope is limited to the caller's own contact book, and same-suggestion accepts are idempotent. The explicit confirmation policy (this runs immediately, unlike destructive/outbound actions) and the note that the caller gets an ordinary result rather than a plan_token add context an agent cannot get from annotations. I'm scoring it down slightly because the description never says what the returned entry contains beyond the deduplicated flag.

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 core action and scope are front-loaded in the first clause, then the mapping rules, then the safety/confirmation policy. Every sentence carries information, but the density is high: semicolons and em-dash appositives pack several distinct rules into single sentences, which slightly raises the chance an agent misses one.

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 three-parameter write tool with annotations and no output schema, this covers the essentials: what is written, what is not copied, idempotency, undo, and why no confirmation gate applies here. The remaining gaps are the format of contact_id and the shape of the returned entry, neither of which is documented elsewhere.

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 carries the full burden. It documents suggestion_id well with example values across source namespaces (mail:123, shared_mail:7, cal:55, tg:9) and explains that note holds the caller's own words rather than the source text. contact_id, however, is only named, not explained (integer vs string, which id space), so one required parameter remains ambiguous.

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?

The description gives a specific verb and resource: it puts one person_context suggestion into a person's timeline, scoped to the caller's OWN contact book. It even spells out the source-to-kind mapping (letter → email, past meeting → meeting, forward → message) and the dedup semantics. It stops short of separating this tool from the sibling add_person_interaction (which likely adds a manually composed entry), so the agent must infer that boundary.

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?

It states the trigger case (converting a person_context suggestion), names delete_person_interaction as the undo path, and explains the repeat-acceptance case (deduplicated=true). What's missing is an explicit when-not: it never says when an agent should use add_person_interaction instead of this tool, even though that sibling is clearly adjacent.

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