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

Annotations already declare write semantics (readOnlyHint=false), non-idempotency, open-world behavior, and non-destructiveness, so the safety profile is covered. The description adds the sensitive-PII constraint, which is genuinely useful, but omits batch-critical behavior: what happens on partial failure, whether pre-existing emails in list_id cause duplicate contacts or errors, and whether there is a max batch size. Note that the PII warning largely restates the custom_fields schema text.

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?

Two tight sentences with the action front-loaded and the constraint second; nothing strays off-topic. Minor redundancy in "at once in bulk," which say the same thing twice.

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, and for a non-idempotent bulk mutation the description should say what a call returns (created count, per-contact errors) and how partial failures are handled. With full schema coverage and solid annotations the gap is not severe, but batch semantics remain underspecified.

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 every parameter (dry_run, list_id, and each contact field) is already documented in structured data; the baseline is 3. The description adds no extra meaning about list_id scoping, dry_run's validation value, or how custom_fields keys are resolved beyond what the schema states.

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 states a specific verb and resource ("Create multiple contacts") and makes the batch scope explicit, which implicitly separates it from the single-record sibling create_contact. It does not name create_contact, upsert_contact, or update_contact directly, so the differentiation is inferable rather than stated.

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 "multiple contacts at once in bulk" – the agent can infer this is the bulk variant, but there is no explicit guidance on when to prefer it over create_contact or upsert_contact, nor any prerequisite such as the target list needing to exist. The sensitive-data sentence is a data constraint, not when-to-use guidance.

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