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

Annotations already establish the safe-read profile (readOnly, idempotent, non-destructive), and the description adds substantial domain behavior beyond them: confirmed sources count once per workspace, pending outcomes stay reserved, and no client-supplied backend receipt is accepted. It also warns that an empty result does not prove absence of sources, which is high-value behavioral context.

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 dense but front-loaded, starting with the two access modes before the caveats. Each clause carries information, though the final sentence is long; it earns its place by preventing misinterpretation of empty results.

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 and five parameters, the description supplies the important semantic framing (what a receipt ledger means, what counts, what an empty result implies). It does not explain the returned record shape or cursor lifetime, but for a read/list tool the coverage is largely sufficient.

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 only 20% (just projectId documented), so the description carries extra burden. It references importId, the optional status filter, and cursor-based paging, but omits limit semantics and refers to the cursor as 'pagination.nextCursor' while the actual parameter is 'cursor', which could confuse the mapping. Partial compensation only, so a baseline 3 is appropriate.

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 resource (durable import states / SourceImport receipts) and two modes of access: paging through the ledger or locating a single importId. The verb is somewhat implicit ('page through', 'locate') but an agent can readily tell this is a read/list tool over import receipts. It is not sharply differentiated from siblings like preview_sources or reconcile_source_import, though the ledger framing helps.

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?

It distinguishes paging from single-record lookup and notes the status filter is optional, giving clear context for how to call it. It also carves out scope by stating this is not an exhaustive source inventory, implying when a different tool may be needed. No explicit named alternative is given, so it stops short of a 5.

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