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

Annotations already flag destructiveHint=true and idempotentHint=false, and the description adds genuinely new behavior: upsert matching on phone_number, dry_run writes nothing, and the important consent rule that status=false records an opt-out and never lifts one. It stops short of stating what happens on partial failure or row skips (only the schema's campaign_id note mentions skipped rows), so it is strong but not complete.

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 dense sentences with zero filler: purpose and limits first, then the fields/tags semantics, then consent behavior, then the import_id/dry_run mechanics. Nothing is repeated from the schema verbatim and each sentence carries new information.

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, 500-row mutation with no output schema, the description covers the critical points: matching, batching, consent semantics, dry-run, and cross-call grouping. What is missing is minor — no description of the response shape beyond the hint that it returns an import_id, and no mention of what happens to invalid or skipped rows.

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 compensates for the highest-value gaps by explaining what fields and tags do downstream (segments, {{field:name}} merge tags) and how opt_in behaves, which the schema alone does not convey. It leaves name, campaign_id, and check_line_types unaddressed in prose, so the compensation is partial rather than complete.

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 opening clause gives a specific verb pair and resource ('Create or update ... contacts'), plus scale ('up to 500 per call') and matching key ('matched by phone_number'), which implicitly separates it from single-record tools like upsert_contact. However, it never names a sibling such as upsert_contact, bulk_update_contacts, or plan_import, so the differentiation is left to inference.

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?

The description explains mechanics (dry_run writes nothing, import_id groups calls) but never states when to use this over alternatives — notably plan_import, which is a likely pre-flight sibling, or upsert_contact/bulk_update_contacts for non-import paths. Usage must be inferred from the batching and import framing rather than being spelled out.

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