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

No annotations are provided, so the description carries the full burden. It transparently discloses the return structure (attribution factor, financed emissions, total, DQ score, audit trail) and mentions PCAF source, which gives insight into the computation. It does not mention side effects or prerequisites, but 'Compute' implies a read-only operation.

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 two sentences, front-loaded with an actionable verb, and every clause adds value—listing specific outputs and the audit trail. There is no redundant or vague phrasing.

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 (multiple outputs, no output schema), the description covers the main return values and relevant context (PCAF source, outstanding-weighted score). It lacks error-handling or input-format details, but for a calculation tool this is nearly 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 coverage is only 50% (holdings has a description, asset_class does not). The description does not elaborate on either parameter, adding no semantic value beyond the schema. It doesn't explain how holdings should be structured or what asset_class values are accepted, leaving a gap for the undocumented parameter.

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 uses a specific verb ('Compute') and resource ('PCAF Part A financed emissions for a portfolio'), clearly stating the tool's function. It distinguishes itself from sibling calculation tools by naming distinct outputs (attribution factor, portfolio total, data-quality score, audit trail), making its purpose unique.

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 usage is implied: an agent would invoke this when asked for PCAF Part A financed emissions. However, there is no explicit when-to-use guidance or mention of alternatives (e.g., calculate_spend) or exclusions, leaving the choice to the agent's inference.

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