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

With no annotations, the description carries full behavioral burden. It extensively discloses key behaviors: single-protein expansion to interactors, capping of large responses, omitted gene lists with preferredNames_omitted, category truncation, and FDR reporting requirements. This goes far beyond typical descriptions and gives the agent critical expectations for invoking and interpreting results.

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 long but well-organized with bullet points and separate sections for behavior, output fields, and metadata. It front-loads the core purpose and immediately follows with execution nuances. While each sentence adds value, the length is substantial; however, given the tool's complexity, the structure earns a high score for clarity and organization.

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 enrichment tool with output schema and multiple edge cases, the description is exceptionally complete. It covers parameter behavior, output field semantics, metadata handling, and cross-tool hints. An agent has enough information to invoke correctly and interpret the response accurately, even without annotations.

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 input schema already includes descriptions for all three parameters (proteins, species, expand_category), though the context reports only 33% coverage, suggesting the schema descriptions may be minimal. The tool description adds meaningful semantics for proteins (single vs. multiple sets) and expand_category (expanded coverage, category selection), but does not add extra meaning for the species parameter beyond its schema description. It partially compensates for low schema coverage, but not fully.

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 the tool's function: 'retrieves functional enrichment for a set of proteins using STRING.' This is a specific verb+resource pairing that distinguishes it from siblings like string_functional_annotation, which provides annotations rather than enrichment. The detailed behavior notes further clarify its unique role among the sibling tools.

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 clear context on how the tool behaves (single vs. multiple proteins, expand_category usage) but does not explicitly state when to prefer this tool over alternatives. It mentions 'When calling related tools, use the same input parameters' but lacks direct comparison or exclusionary guidance like 'use X instead.' Thus, usage intent is implied rather than explicitly differentiated.

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