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

Annotations already establish readOnly, idempotent, non-destructive and closed-world, so the description correctly spends its words elsewhere: newest-first ordering, the constraint that only contacts with an address appear, and a prompt-injection caveat about externally-written data. That caveat is genuinely additive for an agent consuming untrusted fields, though return shape and rate limits are not discussed.

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?

Front-loaded with purpose and scope, followed by sibling routing, filter advice and pagination semantics before the safety note. Dense but each sentence carries distinct information; the filter clause lists are slightly packed but not wasteful.

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?

With an output schema present, return field detail is unnecessary, and annotations cover the safety profile. The description supplies what structured data cannot: ordering, an exclusion rule for address-less contacts, and an untrusted-data warning. Only minor operational details (limits on the 25 max, workspace resolution) are left implicit.

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 83% and the enum descriptions for status/source are already thorough, so the baseline is 3. The description adds the pagination contract beyond the schema — `total` is the match count and `next` is the page cursor — which clarifies how cursor and limit interact.

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 resource and scope ("The workspace's email contacts, newest first") plus the three filter axes, and explicitly names the two siblings it is not (readContact, previewSend). An agent can pick this over related tools without opening any schema.

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?

"For one contact in full ... use readContact; for how many a campaign would reach use previewSend" gives explicit alternatives, and "Narrow with search, status or source rather than paging through everyone" states the preferred usage pattern over raw pagination.

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