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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds real value beyond them: newest-first ordering, the fact that emails are included as a `kind`, the email payload fields (subject, direction, snippet, gmailThreadId), and the explicit 'empty result means nothing was recorded' contract.

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?

Four short sentences, front-loaded with the core action, then the usage cue, then the email detail and the empty-result contract. Every sentence carries information; the phrase 'with what each one was and when' is slightly vague but still functional.

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?

There is no output schema, so the description must carry the return-value burden and it largely does (ordering, email kind and fields, empty-result behavior). The schema covers the limit default/maximum, so the remaining gap is minor, but per-contact vs cross-contact result shape could be clearer.

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 100%, so `name`, `limit`, `person` and `project` are already documented in structured fields; baseline 3 applies. The description adds only that `name` is a single contact and that results are 'logged by this member', but says nothing extra about `person` or `project` semantics.

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?

Uses a specific verb and resource: 'Return the most recent conversations this member logged with one named contact, newest first.' It even signals ordering and scope. It falls short of a 5 because it never names the adjacent tools it differs from (e.g. connections_message_read_messages, connections_contacts_get), leaving the agent to infer the 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?

'Call this for what they last discussed or emailed with someone' gives a clear situational trigger. There is no when-not guidance and no alternative tool is named, so the agent gets context but must infer exclusions against the many other contacts_* siblings.

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