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

No annotations are provided, so the description carries the burden of disclosing behavior. It clearly states that the tool returns all known interactions with any other protein in the database, not just within the query set, which is a key behavioral trait. It also explains that network_type can be set to physical for binding/complex questions and lists evidence score types. However, it does not mention output format, potential large result sets, or any rate limits. Given the output schema exists, the lack of output details is acceptable, but the description could be more transparent about result size or pagination.

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-organized and front-loaded with the core purpose. It uses clear, purposeful bullets for evidence scores and keeps sentences short and actionable. Every sentence contributes to understanding the tool, with no redundant fluff. The length is appropriate for the complexity and the lack of annotations.

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?

The description covers the tool's purpose, usage, differentiation from a key sibling, parameter guidance, and evidence scores. Since an output schema exists, the description does not need to explain return values. Minor gaps include no discussion of species handling or handling of very large result sets, but the description is largely complete for a query tool of this type.

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 only 25%, so the description must compensate. It adds meaningful semantics for network_type ('Set physical only for binding, complex, or co-complex questions') and required_score ('You can filter for strong interactions using required_score'), as well as listing evidence score types (nscore, fscore, etc.). It does not explicitly explain species, but the schema does include a description for species. Compared to a baseline of 1 for low coverage, the description adds substantial value for two of the four parameters.

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 starts with a specific verb and resource: 'Retrieves all interaction partners for one or more proteins from STRING.' It clearly states the scope ('all known interactions between your query protein(s) and any other proteins') and explicitly distinguishes itself from the network tool, which only shows interactions within the input set. This fully clarifies what the tool does and how it differs from a sibling.

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 provides explicit usage guidance: 'Use this when asking "What does TP53 interact with?"' and contrasts it with the network tool, noting the network tool only shows interactions within the input set or a limited extension. It also gives conditional advice: 'If the user refers to "physical interactions", "complexes", or "binding", set the network type to "physical".' This tells the agent when to use this tool and how to adjust behavior for specific user intents.

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