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

With no annotations, the description carries the full burden of behavioral disclosure. It only says 'upload and preview'; it does notstate whether contacts are persisted, whether the file is stored, whether any consent data is validated or mutated, or what side effects occur. The 'consent-declared' phrasing hints at CSV requirements but does not clarify the operation's safety or outcome.

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?

The description is a single, easy-to-scan sentence with no wasted words. However, for a six-parameter operation with a nested mapping object and no output schema, this is closer to under-specification than deliberate conciseness.

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?

The tool has no output schema, no annotations, and a complex nested mapping parameter, so the description should at least clarify what the preview returns and how the import workflow proceeds. It does not describe success/failure signals, preview contents, or the relationship to contact_import_confirm, leaving significant gaps for an agent to infer.

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 83%, so the schema already covers most parameter meanings: csv size limit, basis, source, captured_at format, and organization_id. The description adds no extra parameter-level context, and the nested 'mapping' object remains undescribed in both schema and description. Baseline 3 is appropriate because the schema handles most of the burden.

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 action ('upload and preview') on a specific resource ('consent-declared CSV'), so an agent can tell this is a pre-import validation step. It does not explicitly differentiate from commsharbor_contact_import_confirm or contact_import_get, but the word 'preview' strongly implies an early, non-committing stage.

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 gives no guidance on when to use this tool versus alternatives like contact_import_confirm, contact_import_errors, or contact_import_get. It does not mention the natural workflow of previewing before confirming an import, so the agent must infer the intended sequencing from the tool name alone.

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