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

With no annotations, the description carries the full burden and succeeds. It discloses behavior for single vs multiple proteins, the default 10 partners, the physical network type mapping, the lack of self-interactions/homomers and how to handle such queries, and the effect of required_score adjustments.

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 well-structured with a clear opening purpose, followed by actionable use cases, behavior notes, tuning advice, and a final score-source legend. Each sentence earns its place; the use of bullets and bold improves readability without being verbose.

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 complex tool with 5 parameters and no annotations, the description covers the essential behavioral aspects, limitations, parameter tuning, and even auxiliary knowledge (score source names). Combined with the input schema (which documents parameter formats) and the presence of an output schema, this is complete enough for effective tool usage.

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 description adds valuable meaning beyond the schema, especially for network_type ('set physical only for binding, complex, or co-complex questions'), required_score (when to reduce or increase threshold), and the expansion of score source abbreviations. However, it does not explicitly explain the proteins format or species, which the schema partially does; given low schema coverage, this is a minor gap.

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 'Retrieves the interactions between the query proteins' with a specific verb and resource, and further distinguishes its scope with 'Use this method only when you specifically need to list the interactions between all proteins in your query set.' This differentiates it from sibling tools like string_all_interaction_partners.

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?

It gives explicit guidance on when to use: 'only when you specifically need to list the interactions between all proteins in your query set.' It also covers network type selection, single vs multiple protein behavior, and parameter tuning (reducing required_score for sparse results, increasing for large sets). These are clear contextual instructions for the agent.

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