Export decisions

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

The description adds substantial behavioral detail beyond the readOnlyHint annotation: it describes the return shape, the oldest-first ordering, eval-case grouping, and cursor-based pagination. It does not mention auth or rate-limit behavior, but those are less critical for a read-only export.

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 front-loaded with the core purpose and then efficiently covers return shape and pagination in a few dense but purposeful sentences. Every sentence contributes useful information.

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 carries the burden of explaining returns, and it does so by specifying items, cases, and nextCursor. It also covers ordering and pagination, making the definition complete for an agent to call it correctly.

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 the baseline is 3. The description still adds meaningful semantics by explaining that the returned nextCursor is fed back into the cursor parameter until null, which clarifies the pagination contract beyond the schema field description.

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 clearly identifies the resource and output mode: a paginated export of the decision log, ordered oldest first, intended for evals. It does not explicitly distinguish itself from the sibling list_decisions tool, so it is clear but misses full sibling differentiation.

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 gives clear usage context by saying the export is 'for evals' and explains the pagination loop ('Pass nextCursor back until it is null'). It does not state when not to use this tool or explicitly point to list_decisions for ordinary browsing.

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