aps_compute_compute_axis_weights

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

With no annotations provided, the description carries the full burden for behavioral disclosure. It transparently reveals the computation formula (prompt_tokens + completion_tokens × COMPLETION_MULTIPLIER, default 3.0), the normalization, and the output format (canonical ComputeAxisEntry[] with 6-digit decimal strings summing to ~1.0). This is substantial, although it omits error handling, permissions, and potential side effects, which prevents 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?

The description is compact yet information-dense, covering purpose, formula, output, and usage in roughly four sentences. It is front-loaded with the core action and immediately gives the output type and downstream consumer. Every clause contributes substance without redundancy, making it an excellent example of conciseness.

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 complexity and the absence of an output schema, the description thoughtfully explains the return format and the computation, filling the gap left by no output schema. It also connects to the downstream primitive. While it doesn't cover edge cases, error conditions, or profile details, the provided context is sufficient for typical use, so it scores a 4.

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%, so the schema already documents both parameters. The description adds beyond this by explaining how the parameters are used: 'providers' are per-provider billing records, 'profile' is an optional override, and the formula ties prompt_tokens/completion_tokens to the multiplier. This enriches the semantics beyond the raw schema, meriting a 4 (baseline is 3 for high coverage, and this adds extra value).

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 identifies the tool's function: 'Compute the C-axis fractional weight vector from a list of inference billing records'. It specifies a concrete verb ('compute'), a resource ('C-axis fractional weight vector'), and contextual distinction by referencing the sibling primitive 'aps_construct_attribution_primitive' and implicitly contrasting with 'aps_compute_data_axis_weights' (sibling). This makes the tool's purpose unmistakable.

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 provides clear context for when to use the tool: 'feed directly into aps_construct_attribution_primitive' and lists the input type (inference billing records). It implies the tool is for C-axis weight computation, which differentiates it from siblings like 'aps_compute_data_axis_weights'. However, it lacks explicit 'when not to use' or alternative guidance, so it earns a 4 rather than 5.

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