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

The annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the agent knows this is a safe, read-only operation. The description adds a ValueError if the tensor name is not found, which is useful behavioral context beyond what annotations provide. However, it does not detail how the rank is computed for tensors with different dimensionalities (e.g., matrix vs. higher-order tensor), which could be a behavioral nuance. Given annotations cover safety, a 3 is appropriate.

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 and well-structured: a one-line summary, clear Args, Returns, and Raises sections. It is front-loaded with the main action, and every sentence adds value—there is no filler. This is an example of effective brevity.

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 has one parameter, a rich output schema (int | list[int]), and clear annotations. The description covers the essential usage: it names the parameter, describes the return type, and notes the error condition. A slight gap is not specifying whether the rank can be multi-valued (list[int]) for higher-order tensors, but the output schema covers that. Given the simplicity and available structured data, the description is sufficiently complete.

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 100% since the only parameter 'name' is described in the schema as 'Name of the stored tensor'. The description repeats this with 'The name of the tensor' and adds the context that it must exist in the store (via the Raises section). This adds minimal value beyond the schema but is not harmful. Baseline is 3, and it is met.

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 verb 'computes' and the resource 'rank of a stored tensor', which is specific and distinguishes it from sibling tools like determinant or svd_decompose. It is not just a tautology of the name 'rank' because it clarifies that it operates on tensors in the store. However, it could better differentiate from related concepts like shape or dimensions, but the purpose is clear.

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 implies when to use this tool: when you need the rank of a stored tensor and have its name. However, it does not explicitly state when not to use it or mention alternatives (e.g., use 'view_tensor' to inspect the tensor itself). The context is clear but lacks exclusions or comparisons to siblings.

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