np_diag

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

With no annotations, the description must provide behavioral details. It only restates the schema's dual functionality without adding traits like output shape, diagonal offset behavior, or error conditions. Important numpy behaviors (e.g., flattening input, handling off-diagonals) are omitted.

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 very concise (one sentence), but its brevity sacrifices necessary context. While not verbose, it lacks structure to separate the two modes or provide usage tips. A slightly expanded version would better serve the agent.

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's dual nature and the presence of an output schema, the description should clarify return types (e.g., 2D array for creation, 1D for extraction) and handle edge cases. The minimal description leaves significant gaps for an agent to infer 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?

The input schema has 100% description coverage, providing clear parameter meanings (k as list or int, dtype default). The tool description adds no new information beyond the schema, meeting the baseline expectation of 3.

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 two operations: creating a diagonal array from a list or extracting the diagonal of an array. It uses specific verbs (create, extract) and references the resource. However, it does not explicitly distinguish from siblings like np_eye or np_trace, though the dual functionality is conveyed.

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?

No guidance on when to use this tool versus alternatives (e.g., np_eye for identity matrices, np_trace for sum of diagonal). The description lacks context for choosing between the two modes or how the k parameter affects usage.

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