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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuinely new behavior context: results are based on realized profit only and are historical rather than projected, which sets expectations about output validity.

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?

Two sentences, front-loaded with the core computation and closed with the key caveat. No filler or redundant restatement of the title.

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 two-parameter read-only tool with fully documented schema and annotations, the description covers purpose and the historical/realized framing. It does not say what the return looks like (per-week series vs. final balance), but with no output schema that is a minor omission.

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%, including the ISO-week pattern and amount bounds, so the schema does the heavy lifting. The description only reinforces that the amount is compounded week by week rather than held flat, which is marginal added meaning.

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 states a specific computation (compounding the logbook's realized weekly results from a start week with a given amount) rather than restating the name. Its 'history, not a forecast' clause implicitly separates it from simulate_ladder, but no sibling is named explicitly.

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?

Usage is only implied: 'Realized profit only; history, not a forecast' signals this is a backward-looking calculation, suggesting simulate_ladder is the forward-looking alternative, but the description never states when to choose one over the other.

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