calculate_pcaf

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

No annotations are provided, so the description must disclose behavior. It mentions outputs (attribution factors, data quality score, audit trail) but does not state if there are side effects, authentication needs, or limitations. It doesn't clarify whether it mutates data or just reads. Given no annotations, this is insufficient.

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 sentence that efficiently conveys the tool's purpose and outputs without unnecessary verbosity.

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 description provides context about PCAF Part A and outputs, but lacks details on prerequisites, when to use vs other PCAF tools, or any limitations. Given no annotations, it leaves some context to guesswork.

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 'holdings' parameter has a description outlining the structure (outstanding_amount, denominator, emissions or spend data), but the 'asset_class' parameter is undocumented. Schema coverage is only 50%, so some parameters lack clear semantics.

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 specifies the tool's verb ('Compute'), resource ('PCAF Part A financed emissions'), and output details (attribution factor, portfolio total, data-quality score, audit trail). It distinguishes from sibling tools like calculate_embodied or calculate_spend by focusing on the PCAF Part A standard.

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 use for PCAF Part A financed emissions calculation, but it doesn't explicitly state when to use this over alternative calculation tools (e.g., calculate_spend) or provide exclusion criteria. It gives some context but lacks explicit guidance.

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