Summary
summaryShort summary for a prediction (organism, sequence, mean pLDDT).
Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| qualifier | Yes |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| structures | No | ||
| uniprot_entry | No |
summaryShort summary for a prediction (organism, sequence, mean pLDDT).
| Name | Required | Description | Default |
|---|---|---|---|
| qualifier | Yes |
| Name | Required | Description | Default |
|---|---|---|---|
| structures | No | ||
| uniprot_entry | No |
Changes observed during successful MCP inspections.
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 / structuresAdded value: +{
+ "items": {
+ "properties": {
+ "summary": {
+ "properties": {
+ "confidence_avg_local_score": {
+ "type": "number"
+ },
+ "confidence_type": {
+ "type": "string"
+ },
+ "confidence_version": {
+ "type": "null"
+ },
+ "coverage": {
+ "type": "number"
+ },
+ "created": {
+ "type": "string"
+ },
+ "ensemble_sample_format": {
+ "type": "null"
+ },
+ "ensemble_sample_url": {
+ "type": "null"
+ },
+ "entities": {
+ "items": {
+ "properties": {
+ "chain_ids": {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "description": {
+ "type": "string"
+ },
+ "entity_poly_type": {
+ "type": "string"
+ },
+ "entity_type": {
+ "type": "string"
+ },
+ "identifier": {
+ "type": "string"
+ },
+ "identifier_category": {
+ "type": "string"
+ }
+ },
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "experimental_method": {
+ "type": "null"
+ },
+ "model_category": {
+ "type": "string"
+ },
+ "model_format": {
+ "type": "string"
+ },
+ "model_identifier": {
+ "type": "string"
+ },
+ "model_page_url": {
+ "type": "string"
+ },
+ "model_type": {
+ "type": "null"
+ },
+ "model_url": {
+ "type": "string"
+ },
+ "number_of_conformers": {
+ "type": "null"
+ },
+ "oligomeric_state": {
+ "type": "string"
+ },
+ "preferred_assembly_id": {
+ "type": "null"
+ },
+ "provider": {
+ "type": "string"
+ },
+ "resolution": {
+ "type": "null"
+ },
+ "sequence_identity": {
+ "type": "number"
+ },
+ "uniprot_end": {
+ "type": "number"
+ },
+ "uniprot_start": {
+ "type": "number"
+ }
+ },
+ "type": "object"
+ }
+ },
+ "type": "object"
+ },
+ "type": "array"
+}Output schema / properties / uniprotAccessionRemoved value: -{
- "description": "UniProt accession code",
- "type": "string"
-}Output schema / properties / uniprot_entryAdded value: +{
+ "properties": {
+ "ac": {
+ "type": "string"
+ },
+ "id": {
+ "type": "string"
+ },
+ "segment_end": {
+ "type": "number"
+ },
+ "segment_start": {
+ "type": "number"
+ },
+ "sequence_length": {
+ "type": "number"
+ },
+ "uniprot_checksum": {
+ "type": "string"
+ }
+ },
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already state readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, so the safety profile is covered. The description adds that the output includes organism, sequence, and mean pLDDT, which is mild context about the summary's contents. However, it doesn't disclose any behavioral traits like whether it performs a new prediction or summarizes an existing one, or any rate limits or auth needs.
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 one short sentence, appropriately front-loaded and free of fluff. It could be slightly clearer but is efficient.
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?
Given the tool has an output schema (which presumably documents the return fields), the description needn't explain return values. However, with a single undocumented parameter and no usage guidance, the description is minimally complete but leaves gaps for an agent to confidently invoke the tool.
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 coverage is 0% and the single parameter 'qualifier' has no description. The description does not explain what 'qualifier' means (presumably an identifier like a UniProt accession, as examples show), so it fails to compensate. Baseline for 1 parameter with poor schema coverage would normally be lower, but since the tool has only one parameter and the name hints at its role, a 3 is generous but reflects that the description adds no parameter meaning.
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 says 'Short summary for a prediction (organism, sequence, mean pLDDT)', which gives a verb-resource (summary of a prediction) and hints at returned fields. But 'summary' is vague, and the parenthetical field list is ambiguous about what the tool does with them. It doesn't clearly distinguish itself from the sibling 'prediction' tool.
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 explicit guidance on when to use this tool versus the sibling 'prediction' or others. The description only implies that if you want a brief prediction summary, this is it, but no conditions, exclusions, or alternatives are named.
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.