get_call_resultRead a bounded prior-result chunk by receipt ID.
| Name | Required | Description | Default |
|---|---|---|---|
| offset | No | Character offset; default 0. | |
| api_call_id | Yes | execute call or capability receipt ID. | |
| max_characters | No | Characters: default 8000, max 20000. |
| Name | Required | Description | Default |
|---|---|---|---|
| chunk | No | Result text slice. | |
| api_call_id | No | Receipt ID. | |
| total_characters | No | Full stored result length. |
Changes observed during successful MCP inspections.
Output schema / (root)Previous value: -nullNew value: +{
+ "additionalProperties": true,
+ "properties": {
+ "api_call_id": {
+ "description": "Receipt ID.",
+ "type": "string"
+ },
+ "chunk": {
+ "description": "Result text slice.",
+ "type": "string"
+ },
+ "total_characters": {
+ "description": "Full stored result length.",
+ "type": "integer"
+ }
+ },
+ "type": "object"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior completion. The description adds the 'bounded' chunk semantics and receipt-keyed access, but it does not mention pagination behavior, ordering, or error handling for unknown receipt IDs.
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 a single sentence with an active verb front-loadedcars. 'Read', 'bounded', 'prior-result', and 'receipt ID' each carry real semantic weight with no filler or redundancy.
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 a fully documented schemaasi and an output schema, the description covers the essential scope of the tool. The only gap is lack of explicit sibling-tool routing and any note about chunking with offset/max_characters to a human level.
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 the baseline is 3. The description's 'bounded' and 'receipt ID' language loosely mirrors max_characters and api_call_id, but it contributes no new parameter-level detail beyond the schema.
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 a specific action ('Read'), a specific resource ('bounded prior-result chunk'), and the required key ('receipt ID'). This clearly distinguishes get_call_result from siblings like execute, search_apis, or describe_api.
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 phrase 'prior-result' plus 'receipt ID' gives a clear contextual signal that this tool is for reading output from an earlier call. It does not explicitly contrast with sibling tools or state when not to use it, so it misses the top score.
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.