get_inspection

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

No annotations are provided, so the description carries the full behavioral burden. It discloses the completed-run constraint and pagination intent, but says nothing about permissions, error behavior, ordering, or whether values and weights are returned together.

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 a single front-loaded sentence with no wasted clauses. However, its brevity comes at the cost of under-specification, and the dense jargon is not unpacked.

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?

An output schema exists, so return values need less explanation. Still, for a six-parameter tool with zero schema descriptions and no annotations, the description is too sparse to tell an agent how to call it correctly.

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% across six parameters, so the description must compensate. It only loosely implies pagination via "Page" and weight selection via "pre-edit weights"; it does not explain run_id, limit, offset, value_limit, value_offset, or weight_target.

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?

States a specific action ("Page") and a specific resource ("a completed run's tensor catalog and captured pre-edit weights"). It is clear enough to distinguish this as a read/pagination tool for inspection data, though the domain jargon is not elaborated and no sibling is named.

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?

Provides no explicit when-to-use guidance, no conditions for choosing it over siblings such as get_run or get_capture, and no exclusions. The only implied context is that the run must be completed.

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