Prediction
predictionFull prediction metadata + structure file URLs (PDB, CIF, PAE).
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| qualifier | Yes | UniProt accession, e.g. "P00533" |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| count | No | ||
| items | No |
predictionFull prediction metadata + structure file URLs (PDB, CIF, PAE).
| Name | Required | Description | Default |
|---|---|---|---|
| qualifier | Yes | UniProt accession, e.g. "P00533" |
| Name | Required | Description | Default |
|---|---|---|---|
| count | No | ||
| items | No |
Changes observed during successful MCP inspections.
Output schema / properties / alphafoldVersionRemoved value: -{
- "description": "AlphaFold version used",
- "type": "string"
-}Output schema / properties / countAdded value: +{
+ "type": "number"
+}Output schema / properties / discoveredDateRemoved value: -{
- "description": "ISO date when structure was discovered",
- "type": "string"
-}Output schema / properties / entryIdRemoved value: -{
- "description": "AlphaFold entry identifier",
- "type": "string"
-}Output schema / properties / itemsAdded value: +{
+ "items": {
+ "properties": {
+ "allVersions": {
+ "items": {
+ "type": "number"
+ },
+ "type": "array"
+ },
+ "amAnnotationsHg19Url": {
+ "type": "string"
+ },
+ "amAnnotationsHg38Url": {
+ "type": "string"
+ },
+ "amAnnotationsUrl": {
+ "type": "string"
+ },
+ "bcifUrl": {
+ "type": "string"
+ },
+ "chainId": {
+ "type": "string"
+ },
+ "cifUrl": {
+ "type": "string"
+ },
+ "entityType": {
+ "type": "string"
+ },
+ "entryId": {
+ "type": "string"
+ },
+ "fractionPlddtConfident": {
+ "type": "number"
+ },
+ "fractionPlddtLow": {
+ "type": "number"
+ },
+ "fractionPlddtVeryHigh": {
+ "type": "number"
+ },
+ "fractionPlddtVeryLow": {
+ "type": "number"
+ },
+ "gene": {
+ "type": "string"
+ },
+ "globalMetricValue": {
+ "type": "number"
+ },
+ "isComplex": {
+ "type": "boolean"
+ },
+ "isReferenceProteome": {
+ "type": "boolean"
+ },
+ "isReviewed": {
+ "type": "boolean"
+ },
+ "isUniProt": {
+ "type": "boolean"
+ },
+ "isUniProtReferenceProteome": {
+ "type": "boolean"
+ },
+ "isUniProtReviewed": {
+ "type": "boolean"
+ },
+ "latestVersion": {
+ "type": "number"
+ },
+ "modelCreatedDate": {
+ "type": "string"
+ },
+ "modelEntityId": {
+ "type": "string"
+ },
+ "msaUrl": {
+ "type": "string"
+ },
+ "organismScientificName": {
+ "type": "string"
+ },
+ "paeDocUrl": {
+ "type": "string"
+ },
+ "paeImageUrl": {
+ "type": "string"
+ },
+ "pdbUrl": {
+ "type": "string"
+ },
+ "plddtDocUrl": {
+ "type": "string"
+ },
+ "providerId": {
+ "type": "string"
+ },
+ "sequence": {
+ "type": "string"
+ },
+ "sequenceChecksum": {
+ "type": "string"
+ },
+ "sequenceEnd": {
+ "type": "number"
+ },
+ "sequenceStart": {
+ "type": "number"
+ },
+ "sequenceVersionDate": {
+ "type": "string"
+ },
+ "taxId": {
+ "type": "number"
+ },
+ "toolUsed": {
+ "type": "string"
+ },
+ "uniprotAccession": {
+ "type": "string"
+ },
+ "uniprotDescription": {
+ "type": "string"
+ },
+ "uniprotEnd": {
+ "type": "number"
+ },
+ "uniprotId": {
+ "type": "string"
+ },
+ "uniprotSequence": {
+ "type": "string"
+ },
+ "uniprotStart": {
+ "type": "number"
+ }
+ },
+ "type": "object"
+ },
+ "type": "array"
+}Output schema / properties / mgnifyIdRemoved value: -{
- "description": "MGnify identifier",
- "type": "string"
-}Output schema / properties / modelCreatedDateRemoved value: -{
- "description": "ISO date when model was created",
- "type": "string"
-}Output schema / properties / organismRemoved value: -{
- "description": "Organism name",
- "type": "string"
-}Output schema / properties / plddtRemoved value: -{
- "description": "Mean predicted local distance difference test score",
- "type": "number"
-}Output schema / properties / sequenceRemoved value: -{
- "description": "Amino acid sequence",
- "type": "string"
-}Output schema / properties / sequenceLengthRemoved value: -{
- "description": "Length of protein sequence",
- "type": "integer"
-}Output schema / properties / structuresRemoved value: -{
- "description": "Available structure files",
- "items": {
- "properties": {
- "cifUrl": {
- "description": "CIF format file URL",
- "type": "string"
- },
- "modelPageUrl": {
- "description": "URL to structure details page",
- "type": "string"
- },
- "modelUrl": {
- "description": "URL to structure file",
- "type": "string"
- },
- "paeImageUrl": {
- "description": "PAE image URL",
- "type": "string"
- },
- "paeJsonUrl": {
- "description": "PAE JSON file URL",
- "type": "string"
- },
- "pdbUrl": {
- "description": "PDB format file URL",
- "type": "string"
- }
- },
- "type": "object"
- },
- "type": "array"
-}Output schema / properties / uniprotAccessionRemoved value: -{
- "description": "UniProt accession code",
- "type": "string"
-}Output schema / properties / uniprotIdRemoved value: -{
- "description": "UniProt ID",
- "type": "string"
-}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered. The description adds useful return-content context by naming the concrete artifact types (PDB, CIF, PAE), though the output schema already carries the return shape, so the marginal value is modest.
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?
A single front-loaded sentence with no filler, and the return artifacts are listed immediately. It is arguably too terse to carry the tool's full meaning, but nothing in it is wasted.
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?
With one fully documented parameter and an output schema present, the definition covers enough to invoke the tool correctly. It still leaves the domain ambiguous — nothing tells the agent this is a protein-structure prediction lookup rather than some other kind of 'prediction'.
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% with a single required 'qualifier' documented as a UniProt accession with an example, so the baseline is 3. The description adds nothing about the parameter, not even confirming the qualifier is a UniProt ID.
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 names what is returned (prediction metadata plus PDB/CIF/PAE structure file URLs), which is more informative than the bare name 'prediction'. But it never states what a 'prediction' is or what entity it belongs to (a protein keyed by UniProt accession), and it is a noun phrase rather than a verb+resource statement, so an agent cannot cleanly distinguish it from siblings like uniprot or entity_profile.
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?
There is no when-to-use guidance, no prerequisites, and no mention of alternatives such as uniprot, entity_profile, or resolve_entity. The agent must infer from the name and the UniProt parameter that this fetches structure predictions for a given accession.
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.