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

With no annotations provided, the description carries the full burden. It discloses key behaviors: single protein includes top 10 interactors; multiple proteins restrict to within query set; numeric values produce colored halos (blue positive, red negative) with intensity scaling; and troubleshooting steps like lowering required_score. These details add meaningful transparency beyond the schema.

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 bullet points, an example, and actionable instructions. It is longer than average but each section earns its place, and the primary purpose is front-loaded. No redundancy or fluff.

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 9 parameters and an output schema, the description covers the main scenarios: single vs. multiple proteins, numeric value handling, parameter tuning for empty or large results, and cross-tool consistency. It omits some details (e.g., species, extend_network), but those are described in the schema, and the output schema covers return values. Overall, it is complete enough for an agent to select and invoke correctly.

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 covers all parameters with descriptions, but the description enriches several: proteins (numeric values, halos), network_type (set to 'physical' for binding/complexes), network_flavor (confidence for large queries), and required_score (lower when few interactions). This adds practical meaning beyond the schema, though the description does not mention species or structural options, which are left to the schema.

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 states 'Retrieves a URL to a STRING interaction network image for one or more proteins,' clearly identifying the tool's action (retrieve URL) and resource (STRING interaction network image). It also distinguishes this from sibling tools like string_network_link (interactive page) and string_interactions_query_set (query set) by emphasizing the image output and network visualization.

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 concrete usage guidance: behavior for single vs. multiple proteins, when to set network_type='physical', when to adjust required_score, and how to handle large queries with network_flavor='confidence'. It also instructs the agent to always ask about the interactive STRING page, implying that this tool does not return that link. This is strong guidance, though it does not explicitly name alternative tools for the interactive page.

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