string_interactions

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

No annotations exist, so the description carries the full disclosure burden. It does reveal the read-only query nature and adds genuinely useful interpretive context (higher combined score = more reliable). However, it is silent on result limits, confidence thresholds, whether predicted vs. experimental interactions are included, and behavior for unknown or invalid proteins.

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 compact at roughly four short clauses but is bilingual with visible repetition: the query statement and the use case appear twice ('for protein functional network analysis' / '用于蛋白功能网络分析'). The Chinese half contributes non-redundant detail (input cardinality, score interpretation), so waste is limited, but an agent must parse both languages to obtain the complete picture.

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 low-complexity 2-parameter tool with an output schema (which covers return structure), the description captures the core query behavior, input cardinality, and result interpretation. However, the species parameter being entirely undocumented is a material gap for a multi-species database like STRING, and the absence of annotations leaves operational behavior (limits, failure modes) undisclosed.

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 compensate. It adds real meaning for the proteins parameter ('给定一个或多个蛋白' — one or more proteins) and explains the output scoring, but it never addresses the species parameter (default 9606, without stating it is a taxonomy ID or that 9606 is human) or the accepted identifier format (UniProt vs. gene symbols). These are both needed for correct invocation.

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 a specific verb ('Query'), a precise resource ('protein interaction network from STRING-db'), and the input-output contract (one or more proteins → interaction relationships with reliability scores). Naming STRING-db distinguishes it from interaction siblings like intact_interactions and biogrid_interactions, and the score-semantics note clarifies it is a scored network query, not a sequence or literature search.

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 usage context ('for protein functional network analysis' / '用于蛋白功能网络分析') and scopes the tool to STRING-db data, but it never states when not to use it or names alternatives. With multiple protein-interaction resources among the siblings (intact_interactions, biogrid_interactions, biogrid_gene_interactions), an agent receives no guidance on choosing between them.

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