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

Annotations already cover read-only, idempotent, closed-world and non-destructive behavior, so the bar is lower. The description still adds real value: it declares determinism ('no AI inside'), the fact nothing is logged, that heuristic fallbacks are clearly flagged, and that confidence/warnings are surfaced — all beyond what the annotations say.

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?

It is front-loaded with the transformation and its examples in a single dense sentence plus a worked 'de' example. The enumerated response fields (result, data_confidence, estimated_items[], sources[], data_version, warnings[]) duplicate the existing output schema and are the one part that does not fully earn its place.

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 an output schema and full schema coverage, the description supplies what structured fields cannot: determinism, no logging, heuristic flagging. The only omission is an explicit statement of what happens when the text cannot be parsed at all, which warnings[]/data_confidence only hint at.

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 both text and locale are documented with the same examples, making the description largely redundant here. Its only marginal addition is restating that locale separators are tried first with a flagged heuristic fallback.

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 verb+deliverable: turn human-written number text into an exact decimal, with four concrete input shapes. That clearly separates it from format_number (the inverse direction) and number_to_words, though it never names a sibling explicitly, so sibling differentiation is left implicit.

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 implied by the examples (use it when you hold a human-written numeric string) and the locale-then-heuristic precedence tells the agent how to pick a locale. There is no explicit when-to-use vs when-not-to-use guidance and no pointer to convert_digits or format_number as alternatives.

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