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

The annotations (readOnlyHint=true, idempotentHint=true, destructiveHint=false) are consistent with the description, which adds substantial non-obvious behavior: malformed placeholder syntax is never silently dropped, ICU-based requests are refused rather than partially validated, matching is order-independent with exact multiplicity, and the hard price of 0.03 USDC per bounded job informs cost-aware selection far beyond what structured fields carry.

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?

Every sentence earns its place: definition and checks, per-key error reporting, refusal behavior, scope boundaries, and cost. The core purpose is front-loaded, and the dense parentheticals (conversion types, order-independence, exact multiplicity) replace what would otherwise be ambiguous validation semantics. No redundancy despite covering a complex contract.

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 5-parameter tool with nested objects and no output schema, the description covers input semantics, validation rules, error handling, refusal conditions, and pricing. It hints at the return contract ('reported as a per-key issue in a completed report') but never specifies the report's structure, and the expected format of source_locale is absent—both matters an agent needs for a correct first call.

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 0%, so the description carries the full burden, and it compensates strongly: it explains the syntax enum with concrete examples (double_brace `{{name}}`, printf_named `%(name)s`/`%(name)d`/`%(name)f`), the source-versus-translations relationship, and placeholder multiplicity semantics. However, source_locale is never mentioned and allow_empty is only implied via 'disallowed empty strings', leaving two parameters under-explained.

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?

States the specific verb 'Checks' plus the resource ('structural integrity of translated resource dictionaries against a source dictionary'), and enumerates the exact checks: missing keys, extra keys, disallowed empty strings, and placeholder integrity. It also disambiguates itself from other tool types by asserting 'Never translates anything and never estimates translation quality, tone, or correctness.'

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?

No sibling tools exist, so no alternatives can be named, but the description draws a clear applicability boundary: it is scoped 'to exactly the resources you provide' and refuses ICU MessageFormat plural/select constructs outright. The negative scope statements ('Never translates anything...') tell an agent when NOT to select this tool. It stops short of an explicit 'use this when...' formulation, which is the only reason it is not a 5.

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