export_trajectories

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

With no annotations, the description carries the full burden. It states read-only behavior and refusal for held-out runs, but lacks details on authentication needs, rate limits, or output behavior (e.g., whether it saves a file or returns content). The information provided is adequate but not extensive.

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 with three sentences, front-loading the main purpose and adding key details. No superfluous words, and it avoids repeating obvious 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?

Given the tool has no output schema, the description should explain what the export returns (e.g., file path, success message). It only mentions the export format but omits the outcome. For two simple parameters, it is moderately complete but lacks output clarity.

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 50% (only outPath has a description). The tool description does not add meaning beyond the schema: runId is not explained, and outPath's description is already in schema. The description could have clarified the expected format or constraints for runId, but it does not.

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 the tool exports a run's recorded tool trajectory in a specific format (Hermes-format JSONL) with details about content (one line per action, supervisor labels). It is specific and distinguishes from siblings by mentioning gate results and read-only behavior, though it doesn't explicitly compare to similar export tools.

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 some usage guidance: it is read-only and refuses gate-partitioned runs. However, it does not provide when to use this tool versus siblings like report_export or observation_record, nor does it mention prerequisites or typical scenarios.

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