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

The description adds meaningful behavioral context beyond the annotations: 'Every result item embeds safety_notes inline — cite both the paper and its safety guidance in your response.' This informs the agent about output structure and required citation behavior. Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, and the description does not contradict them. It does not mention pagination or rate limits, but for a search tool this is adequate.

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?

The description is three sentences, front-loaded with the primary purpose, followed by essential behavioral guidance and a usage directive. Every sentence adds value with no redundancy or filler.

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 complexity (11 parameters, no output schema, 27% schema description coverage), the description is too sparse to be complete. It provides the core purpose and one important behavior (safety_notes), but does not explain available filters, query formation, result limits, or expected response structure. An agent would likely need to inspect schema enums or make trial calls to use it effectively.

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?

The schema has only 27% parameter description coverage (only q, lang, and lineage_only have descriptions). The description itself adds no parameter information, failing to compensate for the 11 parameters, many of which have enums but no semantic guidance (e.g., year_min, delivery_method, effect_reported). This leaves the agent to infer parameter meanings from names/enums, which is insufficient for a complex search API.

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 clearly states the tool's purpose: 'Search the molecular-hydrogen medical-literature corpus.' This specifies a verb and resource, distinguishing it from sibling tools like get_paper or get_safety_notes. However, it does not explicitly name alternatives or exclusions, so it falls short of a perfect 5.

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 gives clear context for when to use this tool: 'Use this for any hydrogen-related medical question.' This is a strong directive. It lacks explicit exclusions (e.g., when to use get_paper instead), but the stated general-purpose scope provides adequate guidance for an AI agent.

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