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

With readOnlyHint=true and idempotentHint=true already declaring safety, the description still adds meaningful behavior: readiness 'changes capture rates and the pace-layer drag,' missing revenue or invalid taxonomy are 'reported as skipped, never silently counted,' and anonymous telemetry can be disabled via AIBVF_TELEMETRY_DISABLE=1. It does not spell out the full Accelerate/Fix/Stop decision thresholds, but the underlying rubric is beyond reasonable description scope.

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-loaded with the purpose and the output set, then execution guidance, then caveats and telemetry. Mostly dense and every sentence carries operational weight, though the telemetry sentence is the least relevant to invoking the tool correctly and could be trimmed.

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?

For a nested two-parameter portfolio tool with an output schema present and annotations covering safety, the description supplies the cross-cutting constraints an agent needs: pipeline ordering relative to infer_readiness/validate_portfolio/sequence_portfolio, the single readiness applying portfolio-wide, and what happens to bad data. An output schema exists so return values need not be explained. Only minor gaps (e.g., expected range or edge-case behavior of the skipped set) remain.

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 100%, so the parameter entries already document both fields in depth, establishing a baseline of 3. The description goes beyond that by emphasizing what is easy to miss operationally: 'The single readiness value applies across every initiative' and that organization.revenue_eur is required for EUR values, warning that missing revenue yields skipped rather than silent counts.

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 names a specific verb and resource ('Score several AI initiatives as one AI BVF v1.0 portfolio') and immediately enumerates the exact outputs (counts of Accelerate/Fix/Stop, EUR range, mean score, top-value and top-risk initiative, individual results). It explicitly distinguishes itself from the sibling score_initiative by telling the agent to use this instead of looping that tool one initiative at a time.

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 gives an explicit when-to-use trigger ('when the user has a portfolio document and needs to know what it contains before deciding funding or order'), names the anti-pattern (looping score_initiative), and routes to the right adjacent tools: infer_readiness first when process data exists, validate_portfolio only when the document shape is uncertain, and sequence_portfolio when verdicts need a 90-day order.

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