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

Annotations only provide readOnlyHint=false and destructiveHint=false, which are not informative. The description adds valuable behavioral context: it preserves English terms/numbers/dates, maps Hebrew drug spellings back to English, prefers known_terms and account terms, and counts 3x toward the monthly character quota. This goes beyond annotations and helps the agent anticipate cost and term-handling behavior. No contradiction with 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 purpose and key transformation rules are front-loaded, followed by the quota note. Every phrase earns its place, and the description is efficiently structured for quick comprehension.

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 tool's moderate complexity (3 parameters, nested glossary object) and that an output schema exists, the description fully covers the transformation behavior, parameter usage guidance, and operational constraints (quota). An agent has enough context to call it correctly without additional assumptions.

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 descriptions cover all 3 parameters at 100% coverage, so the baseline is 3. The description adds meaning by explaining the role of known_terms and glossary (mapping Hebrew spellings back to English, preferring patient terms), which clarifies how these parameters interact with the transformation logic. This enriches the schema without redundancy.

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 (turn), a resource (Hebrew clinical question), and an outcome (English query for record search or English model). It clearly distinguishes itself from sibling translation tools by targeting clinical record queries rather than general translation, so an agent can select it appropriately.

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 description implies the use case (clinical record search or English model input) and provides transformation rules (preserving English terms, mapping drug names, preferring patient terms), but it does not explicitly mention when to avoid this tool or point to alternatives like translate or clinical_translate. Some usage guidance is present, but exclusion criteria and alternative selection are left to inference.

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