singularis_gemm

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

With no annotations, the description carries the full burden and does well: it discloses that inputs may be inline or file paths, that output is inline or a .npy path, that a Freivalds-style probe residual check is performed, and that cost scales with 2*m*n*k. It omits any authorization, resource, or failure-mode caveats, keeping it below a 5.

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?

Front-loads the operation, then usage, then inputs, then return behavior, then cost — a sensible order for an agent scanning for relevance. It is dense but each clause adds information; a slightly shorter phrasing of the input/output duality would be tightening, not a defect.

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-shape details need not be restated, and the description wisely adds only the non-schema facts an agent needs: inline vs .npy delivery, the verification probe, and the cost model. For a batched dense multiply with seven arguments, nothing essential is missing.

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%, so the description must compensate, and it largely does: it maps a, b, c0 to inline values and a_path, b_path, c0_path to file paths, and explains beta as the C0 scaling factor via the formula. It does not state that all arguments are optional/defaulted, but the semantic roles are clear.

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 the exact operation as a formula (C = A @ B, optionally A @ B + beta * C0), which is unambiguous and machine-checkable. It is readily distinguishable from siblings like singularis_matrix_exponential, singularis_fft, and singularis_blur, each of which names a different linear-algebra kernel.

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?

Gives clear usage context: 'Use for any large dense multiply, including batches expressed as one tall matrix,' which tells the agent the intended workload shape. It stops short of naming an alternative tool or an explicit when-not-to-use condition, so it earns a 4 rather than a 5.

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