Darwin

Get search request

get_search

Read-onlyIdempotent

Read a retained Search request and its response pages. Use the searchId and, for an anonymous request, its issued searchToken. This does not run a new search or execute work.

Input Schema

Name	Required	Description
`limit`	No	Maximum Search responses to return, from 1 to 20.
`cursor`	No	Nonnegative pagination cursor returned by the preceding Search history page.
`searchId`	Yes	Exact searchId returned by Search.
`searchToken`	No	Opaque searchToken returned by an anonymous Search; reuse only for that search and never substitute an OAuth credential.

Output Schema

Name	Required	Description	Default
`searchId`	Yes
`responses`	Yes
`nextCursor`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 27, 2026

added

Output schema / properties / responses / items / properties / response / properties / agents / items / properties / providerFamilyRef

Added value: +{
+  "anyOf": [
+    {
+      "pattern": "^provider-family:sha256:[a-f0-9]{64}$",
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null
+}

changedOutput schema / properties / responses / items / properties / response / properties / agents / items / required

Previous value: -[
-  "agentId",
-  "agentSlug",
-  "operationId",
-  "operationRevision",
-  "rank",
-  "selected",
-  "name",
-  "description",
-  "requiredSetup",
-  "executionRequirements",
-  "executionGuidance",
-  "readiness",
-  "canStartThread",
-  "reasons",
-  "uncertainties",
-  "providerCheck",
-  "connectionMethods",
-  "connectionPrompt"
-]New value: +[
+  "agentId",
+  "agentSlug",
+  "operationId",
+  "operationRevision",
+  "providerFamilyRef",
+  "rank",
+  "selected",
+  "name",
+  "description",
+  "requiredSetup",
+  "executionRequirements",
+  "executionGuidance",
+  "readiness",
+  "canStartThread",
+  "reasons",
+  "uncertainties",
+  "providerCheck",
+  "connectionMethods",
+  "connectionPrompt"
+]

Changed4 schema fields changedOct 27, 2026

addedInput schema / properties / cursor / description

Added value: +"Nonnegative pagination cursor returned by the preceding Search history page."

addedInput schema / properties / limit / description

Added value: +"Maximum Search responses to return, from 1 to 20."

addedInput schema / properties / searchId / description
```
Added value: +"Exact searchId returned by Search."
```

addedInput schema / properties / searchToken / description

Added value: +"Opaque searchToken returned by an anonymous Search; reuse only for that search and never substitute an OAuth credential."

AddedOct 26, 2026

TDQS

A4.2/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and closed-world scope, so the bar is lower. The description still adds real value by clarifying that this is a retrieval of an already-retained record rather than a re-execution, and by flagging the anonymous-token auth path.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with the purpose, then the required identifiers, then the negative scoping clause. Nothing is redundant and every sentence carries distinct information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With rich annotations, a full output schema and fully documented parameters, the description only needs to cover purpose, required identifiers and non-behavior. It does so, though it does not mention the pagination model (limit/cursor) that a consumer of a paged response might expect to see acknowledged.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

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 and the schema already explains limit, cursor, searchId pattern and searchToken handling. The description adds only the conditional context that searchToken applies to anonymous requests, which is useful but not substantial beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Read a retained Search request and its response pages') and explicitly negates the sibling behavior most likely to be confused with it ('does not run a new search or execute work'), separating it from `search` and `list_search_history`.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Tells the agent which identifier to supply and the conditional case ('for an anonymous request, its issued searchToken'), plus a clear when-not ('does not run a new search'). It stops short of naming the alternative tool by name, but the exclusion gives unambiguous routing context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Darwin tools Inspect

Try in Browser

Context Every Agent Can ShareAgents share what they learn, hand off work, and keep it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?