AIsa Finance

Search AIsa tools and agent-ready plans

search

Read-only

Discover AIsa tools and Plans for external data or actions. Skip tasks that only need supplied content or general knowledge. For multi-step tasks, search the full goal before decomposing it. Use English; put identifiers in known_fields. If has_full_schema=false, call batch_get_schema. Next call batch_quote, not batch_use. Do not search for standalone rewriting, translation, summarization, formatting, or calculations on supplied content. For one capability, use an atomic query. Select a matching capability, date window, and metric. A Plan may cover only part of the task; assess its purpose and follow next_steps_guidance.

Input Schema

TableJSON Schema

Name	Required	Description
`limit`	No	Maximum number of additional direct tool candidates.
`query`	Yes	Natural-language capability or task to discover.
`category`	No	Restrict retrieval to one category. Omit to search everything. (AIsa-only: tool-router has no equivalent.)
`session_id`	No	Reuse the session_id returned by Search in all subsequent tool calls for this task. If omitted, a new session is created.
`known_fields`	No	Known values such as ticker, URL, provider, or identifier that improve retrieval.
`provider_filters`	No	Optional exact catalog provider keys used to narrow retrieval (for example similarweb). Do not use display brands. Omit this field if the exact key is unknown.

Output Schema

TableJSON Schema

Name	Required	Description
`plan`	No
`tools`	Yes
`search_id`	Yes
`session_id`	Yes	Reuse the session_id returned by Search in all subsequent tool calls for this task. If omitted, a new session is created.
`retrieval_mode`	No
`next_steps_guidance`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed17 schema fields changedOct 15, 2026

addedInput schema / $schema

Added value: +"https://json-schema.org/draft/2020-12/schema"

removedInput schema / properties / category / anyOf

Removed value: -[
-  {
-    "enum": [
-      "seo",
-      "finance",
-      "social",
-      "search",
-      "sales",
-      "mail"
-    ],
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

removedInput schema / properties / category / default
```
Removed value: -null
```

changedInput schema / properties / category / description

Previous value: -"Restrict to one category (seo, finance, social, search, sales, mail). Omit to search everything."New value: +"Restrict retrieval to one category. Omit to search everything. (AIsa-only: tool-router has no equivalent.)"

addedInput schema / properties / category / enum

Added value: +[
+  "seo",
+  "finance",
+  "social",
+  "search",
+  "sales",
+  "mail"
+]

addedInput schema / properties / category / type
```
Added value: +"string"
```

addedInput schema / properties / known_fields

Added value: +{
+  "additionalProperties": true,
+  "default": {},
+  "description": "Known values such as ticker, URL, provider, or identifier that improve retrieval.",
+  "type": "object"
+}

changedInput schema / properties / limit / description

Previous value: -"Maximum candidates, 1-10"New value: +"Maximum number of additional direct tool candidates."

addedInput schema / properties / limit / maximum
```
Added value: +20
```
addedInput schema / properties / limit / minimum
```
Added value: +1
```

addedInput schema / properties / provider_filters

Added value: +{
+  "default": [],
+  "description": "Optional exact catalog provider keys used to narrow retrieval (for example similarweb). Do not use display brands. Omit this field if the exact key is unknown.",
+  "items": {
+    "type": "string"
+  },
+  "maxItems": 50,
+  "type": "array",
+  "uniqueItems": true
+}

changedInput schema / properties / query / description

Previous value: -"What you need, in plain language, e.g. 'backlinks of a domain', 'recent tweets by a user', 'insider trades for AAPL'. English works best."New value: +"Natural-language capability or task to discover."

addedInput schema / properties / query / maxLength
```
Added value: +2000
```
addedInput schema / properties / query / minLength
```
Added value: +1
```

addedInput schema / properties / session_id

Added value: +{
+  "description": "Reuse the session_id returned by Search in all subsequent tool calls for this task. If omitted, a new session is created.",
+  "maxLength": 128,
+  "pattern": "^[A-Za-z0-9_-]*$",
+  "type": "string"
+}

addedOutput schema / properties

Added value: +{
+  "next_steps_guidance": {
+    "anyOf": [
+      {
+        "type": "null"
+      },
+      {
+        "type": "array"
+      }
+    ],
+    "items": {
+      "type": "string"
+    }
+  },
+  "plan": {
+    "additionalProperties": false,
+    "anyOf": [
+      {
+        "type": "null"
+      },
+      {
+        "type": "object"
+      }
+    ],
+    "properties": {
+      "canonical_use_case": {
+        "type": "string"
+      },
+      "description": {
+        "type": "string"
+      },
+      "known_pitfalls": {
+        "anyOf": [
+          {
+            "type": "null"
+          },
+          {
+            "type": "array"
+          }
+        ],
+        "items": {
+          "type": "string"
+        }
+      },
+      "plan_ref": {
+        "type": "string"
+      },
+      "primary_tools": {
+        "anyOf": [
+          {
+            "type": "null"
+          },
+          {
+            "type": "array"
+          }
+        ],
+        "items": {
+          "type": "string"
+        }
+      },
+      "recommended_steps": {
+        "anyOf": [
+          {
+            "type": "null"
+          },
+          {
+            "type": "array"
+          }
+        ],
+        "items": {
+          "type": "string"
+        }
+      },
+      "related_tools": {
+        "anyOf": [
+          {
+            "type": "null"
+          },
+          {
+            "type": "array"
+          }
+        ],
+        "items": {
+          "type": "string"
+        }
+      }
+    },
+    "required": [
+      "canonical_use_case",
+      "description",
+      "known_pitfalls",
+      "plan_ref",
+      "primary_tools",
+      "recommended_steps",
+      "related_tools"
+    ]
+  },
+  "retrieval_mode": {
+    "anyOf": [
+      {
+        "type": "null"
+      },
+      {
+        "type": "string"
+      }
+    ]
+  },
+  "search_id": {
+    "type": "string"
+  },
+  "session_id": {
+    "description": "Reuse the session_id returned by Search in all subsequent tool calls for this task. If omitted, a new session is created.",
+    "maxLength": 128,
+    "minLength": 1,
+    "pattern": "^[A-Za-z0-9_-]{1,128}$",
+    "type": "string"
+  },
+  "tools": {
+    "anyOf": [
+      {
+        "type": "null"
+      },
+      {
+        "type": "array"
+      }
+    ],
+    "items": {
+      "additionalProperties": false,
+      "properties": {
+        "arguments_schema": {
+          "additionalProperties": true,
+          "anyOf": [
+            {
+              "type": "null"
+            },
+            {
+              "type": "object"
+            }
+          ]
+        },
+        "description": {
+          "type": "string"
+        },
+        "execution_supported": {
+          "description": "Whether this router can execute and quote the operation; false retains documentation and discovery only.",
+          "type": "boolean"
+        },
+        "execution_unsupported_reason": {
+          "description": "Why execution and quoting remain unavailable through this router.",
+          "type": "string"
+        },
+        "has_full_schema": {
+          "type": "boolean"
+        },
+        "match_reasons": {
+          "anyOf": [
+            {
+              "type": "null"
+            },
+            {
+              "type": "array"
+            }
+          ],
+          "items": {
+            "type": "string"
+          }
+        },
+        "price": {
+          "additionalProperties": true,
+          "type": "object"
+        },
+        "retrieval_debug": {
+          "additionalProperties": false,
+          "anyOf": [
+            {
+              "type": "null"
+            },
+            {
+              "type": "object"
+            }
+          ],
+          "properties": {
+            "fused_rank": {
+              "type": "integer"
+            },
+            "fused_score": {
+              "type": "number"
+            },
+            "lexical_rank": {
+              "type": "integer"
+            },
+            "lexical_score": {
+              "type": "number"
+            },
+            "rerank_admission_rank": {
+              "type": "integer"
+            },
+            "rerank_rank": {
+              "type": "integer"
+            },
+            "rerank_score": {
+              "anyOf": [
+                {
+                  "type": "null"
+                },
+                {
+                  "type": "number"
+                }
+              ]
+            },
+            "runtime_availability": {
+              "type": "string"
+            },
+            "vector_view_ranks": {
+              "additionalProperties": {
+                "type": "integer"
+              },
+              "type": "object"
+            },
+            "vector_view_scores": {
+              "additionalProperties": {
+                "type": "number"
+              },
+              "type": "object"
+            }
+          },
+          "required": [
+            "fused_rank",
+            "fused_score",
+            "lexical_rank",
+            "lexical_score",
+            "rerank_admission_rank",
+            "rerank_rank",
+            "runtime_availability",
+            "vector_view_ranks",
+            "vector_view_scores"
+          ]
+        },
+        "summary": {
+          "type": "string"
+        },
+        "tool": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "description",
+        "has_full_schema",
+        "price",
+        "summary",
+        "tool"
+      ],
+      "type": "object"
+    }
+  }
+}

addedOutput schema / required

Added value: +[
+  "next_steps_guidance",
+  "search_id",
+  "session_id",
+  "tools"
+]

First observedSep 15, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds workflow behavior the annotations cannot: the has_full_schema flag gates a required batch_get_schema call, and the next step after search is batch_quote, not batch_use. It stops short of disclosing retrieval limits or catalog breadth that would push it to a 5.

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

Conciseness4/5

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

It is a dense run of imperatives rather than flowing prose, but each sentence carries a distinct rule (scope, language, workflow branch, negative cases, result interpretation) and the most important scoping guidance is front-loaded. Slightly more compression would help.

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 an output schema present, the description need not explain return values, and it correctly avoids doing so while still referencing the output fields that drive the workflow (has_full_schema, next_steps_guidance). A mutation-free, well-annotated search tool is adequately covered, though catalog scope ('AIsa-only', no external providers) could be stated more explicitly.

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

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the structured baseline is 3. The description adds genuine meaning beyond the schema by telling the agent to write the query in English and to place tickers, URLs, providers, or identifiers in known_fields, which is non-obvious routing guidance for a nested free-form object.

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?

The description opens with a specific verb+resource: 'Discover AIsa tools and Plans for external data or actions.' It also separates this discovery step from the sibling execution tools by naming batch_get_schema, batch_quote, and batch_use and stating when each follows, so an agent can place it in the workflow without opening schemas.

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

Usage Guidelines5/5

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

It gives explicit when-to-use ('tasks needing external data or actions'), when-not ('tasks that only need supplied content or general knowledge'; no standalone rewriting, translation, summarization, formatting, or calculations), and named alternatives (batch_get_schema when has_full_schema=false, batch_quote rather than batch_use). It also specifies query language and atomic-query style, leaving little to inference.

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

All AIsa Finance tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?