predict_ppiPredict the binding-affinity class for a pair of proteins using the IBM MAMMAL biomedical foundation model. Returns label "1" (interacting) or "0" (non-interacting). Inference is CPU-bound and may take up to ~60s.
| Name | Required | Description | Default |
|---|---|---|---|
| protein_a | Yes | Amino-acid sequence, single-letter codes (ACDEFGHIKLMNPQRSTVWY), no FASTA header. | |
| protein_b | Yes | Amino-acid sequence, single-letter codes. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden. It discloses CPU-bound inference and up to 60s latency, which is helpful. However, it does not state whether the tool is read-only or has side effects, nor does it mention idempotency or authentication requirements.
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?
Three concise sentences with front-loaded purpose. No redundant information; every sentence adds value (purpose, output format, performance note).
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 2-parameter tool with no output schema, the description adequately covers purpose, input constraints, output meaning, and performance. Could mention sequence length limits or error handling, but overall sufficient.
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 100%, so baseline is 3. The description adds minor context beyond the schema (e.g., 'no FASTA header'), but does not provide additional value such as length limits or format examples beyond single-letter codes.
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 verb 'predict' and the resource 'binding-affinity class for a pair of proteins', and specifies the output labels. It distinguishes from sibling tools like 'predict_clintox' (clinical toxicity) and 'predict_dti' (drug-target interaction).
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 mentions CPU-bound nature and time, implying it's for offline use, but does not explicitly state when to use vs alternatives or when not to use. No exclusions or alternative tool names are provided.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a clearly distinct purpose: separate get/list for different data types (blog posts, clinical trials, research papers), distinct prediction tools (clintox, dti, ppi), and separate search tools (compounds vs. broad search). No two tools appear to overlap.
Most tools follow the verb_noun pattern (e.g., get_blog_post, list_clinical_trials, predict_dti). The only outlier is mammal_health, which uses a different structure (noun_noun), causing minor inconsistency.
With 15 tools, the server covers a broad oncology research domain without being overwhelming. Each tool serves a clear role, and the count feels well-scoped for the stated purpose.
The tool set covers retrieval and prediction for key domains (papers, trials, drugs, compounds) and includes a cross-dataset search. Minor gaps exist, such as the lack of a dedicated get_compound tool, but search_oncology can partially compensate.