export_corpus

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 several behaviors: it writes a file to the filesystem, records one full comment per line, and includes stub/duplicate flags. It does not say whether an existing corpus.jsonl is overwritten, whether the output/<docket> directory is created, whether the docket must exist, or what happens on failure — material gaps for a write operation.

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?

A single dense sentence that front-loads the action, then the format, then the destination, then the rationale — good ordering with no filler. It is slightly overloaded with parenthetical detail, but every clause carries information.

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 two-parameter write tool with no annotations and no output schema, the description covers the essential output format and default location. It falls short on the undocumented 'path' parameter, overwrite/idempotency semantics, and error conditions, which are the details an agent needs to invoke this safely.

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 partially documents docket_id by showing it expanded into output/<docket>/corpus.jsonl, but the second parameter 'path' is never mentioned, leaving an apparently optional output-location override entirely unexplained. Half the parameters remain undefined in both schema and description.

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 names a specific verb (write/export), a specific resource (the cached corpus), the serialization format (JSONL, one full comment per line with stub/duplicate flags), and the target path. It implicitly contrasts with build_corpus by describing a write-to-disk step, but never names that or any sibling explicitly, so the differentiator is inferred rather than stated.

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 trailing clause 'for skills and subagents to read in batches' hints at the downstream consumer and therefore at when to use it (after the corpus exists, when batch reads are needed), and 'cached corpus' implies build_corpus must have run first. However, there is no explicit sequencing rule, no statement about what to do if the cache is empty, and no exclusion of alternatives.

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