list_interactions

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

Annotations already declare readOnlyHint=true and idempotentHint=true, covering safety. The description adds the behavioral trait 'headline-only list,' which implies condensed output, and mentions it is 'lighter' than get_protein. However, it does not describe pagination behavior, exact response structure, or error conditions. With strong annotations, a 3 is appropriate – it adds some context but not rich behavioral detail.

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 efficient, packing purpose, parameter definitions, and usage context into a few lines. The main purpose is front-loaded, and the rest is organized clearly. It earns its length without fluff, though it could be slightly more scannable by separating parameter explanations into a list.

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 list tool with strong annotations and a well-explained purpose, the description provides enough to call it correctly. It covers filtering, sorting, and the 'headline-only' nature of output. It lacks specific return format or pagination details, but that is acceptable given the tool's simplicity and the presence of get_interaction for deeper detail.

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 must explain parameters. It explicitly defines kind (activates|inhibits|binds|regulates), type (direct|indirect), pathway (substring), min_evidence (minimum papers), and sort (evidence|functions|partner). It does not explain limit, order, or symbol, but symbol is the required protein identifier and limit/order are common and inferable. The explanation of the key filtering parameters is strong, so a 4 is justified.

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 a specific verb and resource: 'Filtered, sorted, headline-only list of a protein's interactions.' It explicitly contrasts with siblings by calling itself 'Lighter than get_protein' and directing drill-in to get_interaction, so the agent knows exactly what this tool does and how it differs.

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 explicit when-to-use guidance: 'use it for targeted questions' with an example, and names the alternative 'get_protein' and the follow-up 'get_interaction(id)'. It also explains the filter parameters (kind, type, pathway, min_evidence, sort) which tell the agent how to tailor the query, leaving no ambiguity about selection.

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