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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's added value is the return shape: status enum values, current phase, counts, findings, errors, resumability, and the finished report. The one behavioral omission is what happens on an unknown or expired import_id.

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?

Purpose and endpoint lead, and the return-value enumeration follows in a single tight sentence. The list of returned fields is long but each item carries information an agent needs to interpret the response.

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 no output schema, the description takes on the burden of describing returns and does so thoroughly, including status values and resumability. What remains missing is procedural guidance around polling and handling of the resumable flag, which likely maps to another operation not named here.

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 both parameters are documented structurally, but the schema text is bare boilerplate ('import_id (required)'). The description's endpoint template hints that import_id is the path segment, yet organization_id is never explained and no ID format or scoping rules are added.

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 ('Follow a background import') and pins it to an endpoint, GET /v1/imports/{id}, which makes clear it is a read of an existing import rather than the import.postgres/import.supabase kickoff siblings. It stops short of naming those siblings explicitly, so the differentiation is inferential 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?

'Follow' implies polling a previously started import, but the description never says to call this after import.postgres/import.supabase, nor gives any polling cadence or termination condition. Usage is implied by context rather than prescribed.

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