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

Adds substantial context beyond the annotations: the import runs in the background, a second request is queued rather than lost, progress is checked via channels.list(account_id=...), history_import.skipped/not_imported report exclusions, and the call is safe to repeat. These behaviors are not derivable from the readOnlyHint=false/destructiveHint=false annotations alone.

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 the outcome statement, then grouped into a contacts paragraph, an import_history paragraph, and operational limits. Every sentence carries actionable information with no filler.

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 4 parameters and no output schema, the description covers what the tool does, how to structure input, the async processing model, and how to verify results externally. Nothing an agent needs to invoke it correctly is missing.

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?

Although schema coverage is 100% (baseline 3), the description expands meaning well beyond the schema: it enumerates the contact structure fields, explains what 'details' may carry, tells when to supply conversation_id, and unpacks the import_history enum values in operational terms. This is genuine added value, not repetition.

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 verb and resource ('Load people into a custom channel account') plus the observable outcome (conversations titled with names, contacts get cards in the workspace). This is clearly distinguishable from siblings like contacts_sync or channels_update_profile at a glance.

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?

Gives concrete usage rules for the import_history parameter ('answered' vs 'all' vs omit for names only) and practical conditions (up to 5000 per call, re-loading is safe). It stops short of routing the agent away from sibling tools, so it is strong but not exhaustive.

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