Obtain diagnostic data from the MetaDome service to assess operational status and resolve query issues.
Signature: get_diagnostics(response_mode=).
| Name | Required | Description | Default |
|---|---|---|---|
| response_mode | No | Mode. |
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v0.3.7Input schema / properties / response_mode / defaultRemoved value: -"compact"Input schema / properties / response_mode / descriptionPrevious value: -"Verbosity: minimal|compact|standard|full (default compact)."New value: +"Mode."Input schema / properties / response_mode / typeRemoved value: -"string"Output schema / (root)Previous value: -nullNew value: +{
+ "$defs": {
+ "M": {
+ "additionalProperties": false,
+ "patternProperties": {
+ "^(tool|request_id|capabilities_version)$": {
+ "type": "string"
+ },
+ "^data_versions$": {
+ "$ref": "#/$defs/V"
+ },
+ "^elapsed_ms$": {
+ "type": "integer"
+ },
+ "^next_commands$": {
+ "items": {
+ "additionalProperties": false,
+ "minProperties": 2,
+ "properties": {
+ "arguments": {
+ "propertyNames": {
+ "const": "query"
+ },
+ "type": "object"
+ },
+ "tool": {
+ "type": "string"
+ }
+ },
+ "type": "object"
+ },
+ "type": "array"
+ },
+ "^unsafe_for_clinical_use$": {
+ "const": true
+ }
+ },
+ "required": [
+ "tool",
+ "request_id",
+ "data_versions",
+ "unsafe_for_clinical_use"
+ ],
+ "type": "object"
+ },
+ "V": {
+ "additionalProperties": false,
+ "minProperties": 8,
+ "patternProperties": {
+ "^(assembly|gencode|uniprot|gnomad|clinvar|pfam|metadome_app|data_doi)$": {
+ "type": "string"
+ }
+ },
+ "type": "object"
+ }
+ },
+ "oneOf": [
+ {
+ "additionalProperties": false,
+ "properties": {
+ "_meta": {
+ "$ref": "#/$defs/M"
+ },
+ "build": {
+ "additionalProperties": false,
+ "minProperties": 3,
+ "patternProperties": {
+ "^(version|git_sha)$": {
+ "type": "string"
+ },
+ "^built_at$": {
+ "type": [
+ "string",
+ "null"
+ ]
+ }
+ },
+ "type": "object"
+ },
+ "cache_stats": {
+ "additionalProperties": false,
+ "minProperties": 3,
+ "patternProperties": {
+ "^(on_disk|lru_size)$": {
+ "type": "integer"
+ },
+ "^data_version$": {
+ "type": "string"
+ }
+ },
+ "type": "object"
+ },
+ "capabilities_version": {
+ "type": "string"
+ },
+ "data_versions": {
+ "$ref": "#/$defs/V"
+ },
+ "dropped_summary": {
+ "type": "string"
+ },
+ "metrics": {
+ "additionalProperties": false,
+ "minProperties": 5,
+ "patternProperties": {
+ "^(requests|errors)$": {
+ "type": "integer"
+ },
+ "^error_rate$": {
+ "type": [
+ "number",
+ "null"
+ ]
+ },
+ "^latency_ms$": {
+ "additionalProperties": false,
+ "minProperties": 5,
+ "patternProperties": {
+ "^(p50|p95|p99|max|sampled)$": {
+ "type": "integer"
+ }
+ },
+ "type": "object"
+ },
+ "^per_tool$": {
+ "additionalProperties": {
+ "additionalProperties": false,
+ "minProperties": 2,
+ "patternProperties": {
+ "^(requests|errors)$": {
+ "type": "integer"
+ }
+ },
+ "type": "object"
+ },
+ "type": "object"
+ }
+ },
+ "type": "object"
+ },
+ "success": {
+ "const": true
+ }
+ },
+ "required": [
+ "success",
+ "_meta",
+ "cache_stats",
+ "build",
+ "metrics",
+ "data_versions",
+ "capabilities_version"
+ ]
+ },
+ {
+ "additionalProperties": false,
+ "patternProperties": {
+ "^(message|recovery_action|field|hint)$": {
+ "type": "string"
+ },
+ "^_meta$": {
+ "$ref": "#/$defs/M"
+ },
+ "^allowed_values$": {
+ "items": {
+ "type": "string"
+ },
+ "type": "array"
+ },
+ "^error_code$": {
+ "enum": [
+ "invalid_input",
+ "not_found",
+ "ambiguous_query",
+ "upstream_unavailable",
+ "rate_limited",
+ "internal"
+ ]
+ },
+ "^retryable$": {
+ "type": "boolean"
+ },
+ "^success$": {
+ "const": false
+ }
+ },
+ "required": [
+ "success",
+ "_meta",
+ "error_code",
+ "message",
+ "retryable",
+ "recovery_action"
+ ]
+ }
+ ],
+ "type": "object"
+}v0.3.1Output schema / (root)Previous value: -{
- "additionalProperties": true,
- "properties": {
- "_meta": {
- "additionalProperties": true,
- "type": "object"
- },
- "build": {
- "additionalProperties": true,
- "type": "object"
- },
- "cache_stats": {
- "additionalProperties": true,
- "type": "object"
- },
- "candidates": {
- "type": "array"
- },
- "data_available": {
- "type": "boolean"
- },
- "data_versions": {
- "additionalProperties": true,
- "type": "object"
- },
- "error_code": {
- "type": "string"
- },
- "field": {
- "type": "string"
- },
- "hint": {
- "type": "string"
- },
- "message": {
- "type": "string"
- },
- "metrics": {
- "additionalProperties": true,
- "type": "object"
- },
- "recommended_citation": {
- "type": "string"
- },
- "recovery_action": {
- "type": "string"
- },
- "retryable": {
- "type": "boolean"
- },
- "success": {
- "type": "boolean"
- },
- "upstream_reachable": {
- "type": "boolean"
- }
- },
- "required": [
- "success"
- ],
- "type": "object"
-}New value: +nullv0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds no behavioral information beyond the readOnlyHint=true annotation. It does not contradict the annotation, but it fails to disclose any additional behavior such as what the diagnostics cover, how the response_mode affects results, or any limitations. With no extra context, the agent is left with only the annotation, which is insufficient.
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 extremely short but not concise in a meaningful way; it is under-specified. It contains only a signature line and fails to provide essential information. Every sentence (or fragment) should earn its place, but here it adds no value.
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 tool with multiple siblings, a single parameter, and an output schema, the description is completely inadequate. It does not explain what diagnostics are returned, how the response_mode impacts the output, or any other relevant context. The agent cannot confidently invoke this tool based on this description.
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% (the parameter 'response_mode' is documented with an enum and a brief description 'Mode.'). The tool description itself only mentions the parameter name in a signature and adds no meaning. Per the rubric, the baseline is 3 when schema coverage is high, and the description does not detract from that, but it also does not enhance it.
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 is only a signature line 'get_diagnostics(response_mode=)' with no verb, resource, or explanation of what diagnostics are retrieved. It essentially restates the tool name and adds no semantic content, failing to distinguish it from sibling tools like get_server_capabilities or get_tolerance_landscape.
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 guidance on when to use this tool versus any alternative. No context, conditions, or exclusions are provided, leaving the agent to guess the appropriate situation for calling get_diagnostics.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.