inbox_export

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

The description discloses key behavioral traits beyond the annotations: it copies attachments next to inbox.json and rewrites paths to relative, marks messages as taken, requires target to be a fresh directory, and warns about the consequence of passing raw rows (attachments marked missing). These are side effects and preconditions not captured in the schema or annotations, providing rich transparency.

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 concise and well-structured. It opens with a one-sentence summary, then elaborates with focused paragraphs on usage, workflow, and key parameter requirements. Every sentence adds value, with no fluff or redundancy. The inclusion of a warning (raw rows) and edge-case handling (include_taken) is packed efficiently.

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?

Given the tool's complexity (6 params, no output schema) and the rich annotations, the description covers the essential aspects: what the tool produces (a self-contained folder), when to use it (archiving), how it integrates with other tools (inbox_done), critical parameter constraints, and a failure mode. This is complete for the intended use case and leaves minimal gaps.

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?

The schema has no parameter descriptions (0% coverage), so the description must compensate. It adds crucial semantics for target ('must be a fresh directory') and include_taken ('rebuild a bundle... only route by which attachments can still reach the archive'). However, it does not explain chat, limit, since, or until beyond their names, leaving their meaning and usage partially implicit (e.g., 'range' hints at since/until). While some parameters are covered, the incomplete compensation for the schema gap warrants a mid-range score.

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 opens with a clear, specific action: 'Write a self-contained folder for a range, ready to import into an archive.' It explicitly contrasts with inbox_fetch, stating 'Prefer this over inbox_fetch whenever the messages are going into the archive,' which distinguishes its purpose from the sibling tool. The verb 'write' and resource 'folder' make the operation unambiguous.

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 explicit when-to-use guidance: 'Prefer this over inbox_fetch whenever the messages are going into the archive.' It also instructs on the required workflow ('call inbox_done once they are recorded') and when to set include_taken ('rebuild a bundle for messages handed out earlier but never archived'). This is comprehensive and actionable.

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