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

Beyond the annotations (readOnly, idempotent, non-destructive), the description discloses two critical behavioral traits: 'after' figures are counterfactual (the proposed portfolio was not held) and the tool never recommends a course of action. It also states that both portfolios are evaluated on the same price history, which prevents an agent from assuming a before/after comparison across different histories.

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?

Three short sentences, each doing distinct work: the primary action, the substantive dimensions, and the decision-agnostic limitation. The key phrase 'before it is made' is front-loaded, and there is no filler or repetition of schema details.

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 output schema exists and annotations already declare the safety profile, the description covers what an agent needs to select and call the tool: purpose, what is measured, counterfactual semantics, and the limitation that it gives no recommendation. The optional window/base parameters are sufficiently documented by the schema.

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%: current and proposed are documented as {ticker: weight} objects, start/end are dates, and base is a currency. The description adds conceptual context (same price history, what is measured) but does not add format or syntax details beyond the schema, so the baseline of 3 is appropriate.

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 the action 'Measure a change before it is made', names the resource (current portfolio vs proposed portfolio), and specifies the dimensions compared (structure, risk, worst falls, additions/removals). It distinguishes itself from generic compare tools by stressing the counterfactual nature of the 'after' figures, which is exactly what separates it from siblings like compare_portfolios or measure_portfolio.

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?

It explicitly frames the use case: testing a change before applying it, and explicitly states what the tool will not do ('Never says whether to make the change'). It does not name sibling tools or give when-not conditions relative to them, but the counterfactual and pre-change language gives the agent a clear, non-implied usage context.

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