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

With no annotations, the description carries the full burden. It discloses the consent/source-access requirement, which is useful, but it does not state whether the operation is a mutation, what side effects occur (e.g., creating a new version), whether it is idempotent, or what the response looks like. The 'versioned' hint is vague.

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 two sentences and front-loads the purpose. The caveat about consent is added after. It is concise and to the point, though it lacks detail in other areas.

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 tool has 3 required parameters, no output schema, and no annotation coverage. The description does not explain what 'prepare' entails, what the parameters refer to, or what the return value is. This is severely inadequate 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 description coverage is 0%, so the description must compensate. It lists formats (JSONL, CSV, graph) that likely map to the 'format' parameter, but it does not explicitly link them. The 'id' and 'idempotencyKey' parameters are unexplained, and the nested 'format' object structure is not clarified.

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 states a specific verb ('prepare') and resource ('export') with explicit formats (JSONL, CSV, graph) and the qualifier 'versioned'. This distinguishes it from sibling 'read_research_export', which likely reads an existing export.

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 provides no guidance on when to use this tool versus alternatives. It mentions a prerequisite (consent and source access) but does not clarify scenarios where this tool is appropriate or when to use other research/export tools.

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