edgegate_capture_reference

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

With no annotations, the description takes on the full transparency burden. It discloses that it returns a job_id, requires admin access, and clarifies the behavioral difference between the two flavors (auto-FP16 vs golden). It could additionally mention error conditions or what state changes occur, but the core behavior is clearly communicated.

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 compact and front-loaded, explaining the purpose in the first sentence and then providing essential usage constraints and return behavior in a few sentences. Every sentence adds value without redundancy.

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 is complex with six parameters, no output schema, and a polling requirement. The description covers the essential workflow: what it does, the required flavors, the return type, and the permission level. It doesn't detail error handling or how to poll (leaving that to sibling tools), but it is sufficiently complete for an agent to initiate and understand the result.

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 coverage is high (83%), so baseline is 3. The description adds meaningful value by introducing the mutual exclusivity constraint ('EXACTLY one flavor') not present in the schema, and clarifies the semantic distinction between hf_repo and reference_upload_artifact_id. This goes beyond the schema's basic property descriptions.

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 triggers a 'reference-oracle capture' and defines it as the baseline the Behavioral Gate diffs against. It specifies the exact verb and resource, and the mention of two flavors (hf_repo and reference_upload_artifact_id) distinguishes it from other edgegate tools like edgegate_run_gate or edgegate_publish_eval_set.

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 explicit guidance to 'Specify EXACTLY one flavor' and explains the two options, which is crucial for correct usage. It also notes the admin requirement and that it returns a job_id to poll, implying a follow-up status tool. However, it doesn't explicitly point to alternative tools or say when not to use this tool.

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