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

Annotations already declare readOnlyHint=false and destructiveHint=true, so safety framing is partly covered. The description adds useful behavior ('reads the whole file at once') and explains the column-mapping heuristic, but says nothing about what happens on malformed rows, duplicates, partial failures, or whether an import can be undone — notable omissions for a destructive bulk write with no output schema.

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 action and accepted formats, then the negative guidance, then parameter routing. Dense but nearly every clause carries information; the em-dash aside about the column mapper is worth its length, though the sentence structure is slightly run-on.

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?

No output schema exists, so the description should say what an import produces or how failures surface. It covers input sourcing and column inference well, but an agent still cannot predict return values, duplicate handling, or error behavior for a destructive operation on many records.

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 100%, so baseline would be 3, but the description adds real meaning: name is the fallback when object_id is unknown, object_id comes from search_graph_objects of type 'file', and description feeds the column mapper (the 'Ref' is a phone number example). Only target_type's row semantics beyond the enum is left to the schema.

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 ('Import every contact or company from a file') and enumerates accepted formats (CSV, spreadsheet export, .vcf, zip). It also contrasts the bulk path with the wrong per-record path, so an agent can distinguish it from create_graph_object and read_file without opening a 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?

Gives explicit when-to-use ('whenever they want more than a couple of records created from a file') and an explicit anti-pattern ('never read a contact list with read_file and create the records one at a time'). It also prescribes the prerequisite lookup (search_graph_objects with type 'file') and the object_id/name fallback.

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