plan_dataset

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

Annotations provide readOnlyHint=true, and the description adds meaningful behavioral detail beyond that: it reads only the manifest, not the corpus, and explicitly lists operations it does not perform. This is valuable transparency with no contradiction.

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?

Three tight sentences, with the core purpose in the first line and the key limitations following. Every sentence adds useful information and the structure is easy to scan.

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?

The description covers purpose, scope, and important non-behaviors, and references the training-script usage context. It lacks output/return details and parameter-specific guidance, but given the simple tool shape and read-only annotation, it is fairly complete.

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 0%, so the description must compensate. It mentions manifest validation and cache sizing, but gives no explanation of cache_gib or reserve_gib semantics, units, limits, or how they interact. The parameter names alone are not enough.

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?

Description uses specific verbs and resources: 'Validate a local immutable shard manifest and size a bounded cache for large datasets.' It clearly distinguishes itself from sibling tools focused on runtime, workspace, and script execution.

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?

The description gives clear context: it reads only the manifest and does not provision VMs or contact Drive. It stops short of naming an explicit alternative tool or a precise when-to-use versus when-not-to-use condition, but the exclusions are strong usage guidance.

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