arabic_prepare_for_search

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

Annotations already carry readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so no safety disclosure is owed. The description adds real behavioral texture beyond that: the transformation is lossy (and therefore reports lossiness), is deterministic enough for its fingerprint to be 'stable', and returns warnings plus a full audit trail. Nothing contradicts the 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?

Two sentences with no filler: the first front-loads purpose and use cases, the second itemizes the returned artifacts. Every clause earns its place and nothing is redundant with the input schema or annotations.

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?

An output schema exists, so the listed return fields do not need exhaustive explanation. The main remaining gap is profile selection semantics: with three transformation-strength levels and no guidance on when each is appropriate, an agent cannot reason correctly about the core tradeoff. Given the moderate complexity, the description is adequate but not complete.

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 prose carries the full burden. The description gives no hint of how to choose or interpret the 'profile' parameter — the three enum values ('conservative', 'search', 'aggressive') are left entirely unexplained apart from the 'search' default. It only partly compensates by scoping 'text' to Arabic/mixed input, so the most decision-heavy parameter is undocumented.

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 action ('Prepare…text') plus a clear resource ('Arabic/mixed text') and concrete use cases (search, RAG, deduplication). It names the returned artifacts (tokens, SHA-256 fingerprint, lossiness, audit trail), making the tool's job unambiguous. It never distinguishes itself from the sibling 'arabic_normalize' explicitly, so it misses the top score.

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 phrase 'for search, RAG, and deduplication' gives an implied context for when to reach for this tool. However, the description never mentions the sibling 'arabic_normalize', gives no when-not-to-use guidance, and provides no explicit exclusion criteria, leaving selection between the two tools to inference.

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