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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and closed-world scope, so the safety profile is covered. The description adds only that the dataset originates from an Actor run. It says nothing about pagination behavior, default limits, ordering defaults, or what happens with an invalid/empty datasetId.

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?

Two short sentences, front-loaded with the purpose followed by the usage condition, with no filler. It is arguably too terse for an eight-parameter paginated read, but nothing in it is wasted or misplaced.

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?

An output schema exists, so return-shape explanation is not required, and all parameters are covered by the schema. However, for a paginated, field-shaping read tool, the description omits any hint about paging through large datasets or how limit/offset interact, leaving the agent to infer retrieval strategy.

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 100%, so all eight parameters (limit, offset, desc, clean, fields, omit, flatten, datasetId) are already documented in the schema. The description adds no meaning on top of that, which is the expected baseline when the schema does the work.

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: 'Returns rows from a dataset produced by an Actor run.' An agent can tell this is a read of dataset items rather than an Actor run or key-value store operation. It does not name a sibling it is not, but no sibling in the list is a closely competing dataset-item reader.

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?

'Use when you have a datasetId and need the result items' gives a clear precondition and intent, which implies when to reach for it. It offers no exclusions, no mention of what to use when you do not yet have a datasetId (e.g. fetching the run first), and no guidance among the field-shaping options.

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