essay.debug.export

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

With no annotations, the description carries the full burden, and it does disclose real behavior: it packs only logs already on disk, a missing log stays missing rather than being regenerated, an empty pack is refused, and draft-then-confirm does not apply (so there is no confirmation gate). The remaining gap is what the caller receives and where the file lands, which is left entirely implicit, so it falls short of a 5.

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 trigger is front-loaded and the piece is short with no filler, so every sentence carries some operational content. However, the telegraphic fragments ('Use zip-for-ferry.', 'No chat card.', 'Student chat does not name those files.') are terse to the point of being cryptic for a caller unfamiliar with the domain, which costs some clarity.

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?

For a zero-parameter operator tool with no annotations and no output schema, the description covers the trigger, the source of the data, and the failure mode of an empty pack. It never explains what the call yields or where the packed file is placed, and with no output schema to fall back on, that is a meaningful hole for a caller who must decide what to do after invoking it.

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 tool takes zero parameters and the schema is a bare object, so there is no parameter meaning for the description to add. Baseline 4 applies.

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 states a specific verb and resource: it packs the run logs already on disk into a single file, for the operator. That is clearly distinguishable from essay.debug.wipe, the other debug-sibling, though the description never names a sibling tool to contrast with. Purpose is unambiguous without opening any schema.

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 an explicit trigger ('When the operator asks for the run logs in one file, call this') and an explicit anti-pattern ('Do not paste a truncated run log into chat'). It also narrows the audience to the operator and says the student chat does not surface these files. What is missing is guidance on when NOT to export, or which sibling to use if the caller is not the operator.

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