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

The description adds meaningful behavioral context beyond the annotations: it explicitly states the tool is a pure deterministic calculation with no network, auth, or side effects, and that capacity overflow is never hidden but reported as a conflict or deferral. It also clarifies it does not mutate or re-score anything. Nothing contradicts the readOnly, idempotent, or destructive annotations.

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 dense but each sentence earns its place. It front-loads the critical call placement ('CALL THIS after score_portfolio'), gives the essential scope, then covers inputs and behavior without repetition or filler.

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 complex tool with nested inputs and five parameters, the description covers required input types, valid alternative input shapes, constraint behavior, overflow semantics, and integration with recommend_improvements. An output schema exists, so return-value details are not needed in the description. The context is complete enough for an agent to invoke it correctly without ambiguity.

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?

Although schema coverage is 100%, the description adds high-level semantic guidance that the schema alone doesn't provide: pass the output of score_portfolio directly into portfolio, or use organization plus initiatives; readiness sets capture rates and pacing; horizon_days splits the plan into three equal windows; and max_parallel_per_function caps simultaneous change per function per wave. This helps the agent make correct invocation decisions quickly.

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 opens with a specific verb and resource—turn a scored AI portfolio into three waves with gates over a configurable horizon—and clearly states what it does not do: it does not change verdicts or re-score the business case. It also distinguishes itself from score_portfolio and recommend_improvements by positioning the tool's role in the workflow.

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 explicitly says 'CALL THIS after score_portfolio when the user asks what to stop, fund first, defer or fit into the next 90 days.' It also names recommend_improvements as a required prerequisite for Fix initiatives before wave placement is treated as permission to proceed, so the agent receives concrete when-to-use and when-not-to-proceed guidance.

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