Skip to main content
Glama

AIsa Web Search & Research

by one.aisa
OverviewDiscussionsAdmin

Exa Agent Runs submit

post_exa_agent_runs
Destructive

Owner-scoped local asynchronous job lifecycle. Disabling new admission does not disable existing job reads or cancellation. Runtime availability and access policy also apply.

Default request estimate: $0.1 USD (not a fixed price). Account-specific pricing and final settlement may differ.

Input Schema

NameRequiredDescriptionDefault
bodyYes
Idempotency-KeyYesTrimmed UTF-8 length must be 1 through 191 bytes.
X-AISA-Cost-ModeNoReturn a read-only cost quote instead of submitting a job.
X-AISA-Max-Price-USDNoOptional maximum customer authorization in USD, validated by the runtime price parser.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changed
    • addedInput schema / additionalProperties
      Added value: +false
    • addedInput schema / properties / body
      Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "effort": {
+      "default": "minimal",
+      "description": "Only minimal effort is supported; omitted, empty and null values normalize to minimal.",
+      "enum": [
+        null,
+        "",
+        "minimal"
+      ],
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "query": {
+      "description": "Non-empty query after trimming whitespace.",
+      "pattern": "\\S",
+      "type": "string"
+    },
+    "systemPrompt": {
+      "type": [
+        "string",
+        "null"
+      ]
+    }
+  },
+  "required": [
+    "query"
+  ],
+  "type": "object"
+}
    • removedInput schema / properties / effort
      Removed value: -{
-  "default": "minimal",
-  "description": "Only minimal effort is supported; omitted, empty and null values normalize to minimal.",
-  "enum": [
-    null,
-    "",
-    "minimal"
-  ],
-  "type": [
-    "string",
-    "null"
-  ]
-}
    • removedInput schema / properties / query
      Removed value: -{
-  "description": "Non-empty query after trimming whitespace.",
-  "pattern": "\\S",
-  "type": "string"
-}
    • removedInput schema / properties / systemPrompt
      Removed value: -{
-  "type": [
-    "string",
-    "null"
-  ]
-}
    • changedInput schema / required
      Previous value: -[
-  "Idempotency-Key",
-  "query"
-]New value: +[
+  "Idempotency-Key",
+  "body"
+]
  2. Changed17 schema fields changed
    • changedInput schema / properties / Idempotency-Key / description
      Previous value: -"Unique key (1 to 191 characters) that makes the submit idempotent. Re-submitting with the same key and request fingerprint returns the original run."New value: +"Trimmed UTF-8 length must be 1 through 191 bytes."
    • removedInput schema / properties / Idempotency-Key / maxLength
      Removed value: -191
    • addedInput schema / properties / Idempotency-Key / pattern
      Added value: +"\\S"
    • addedInput schema / properties / X-AISA-Cost-Mode
      Added value: +{
+  "description": "Return a read-only cost quote instead of submitting a job.",
+  "enum": [
+    "quote"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / X-AISA-Max-Price-USD
      Added value: +{
+  "description": "Optional maximum customer authorization in USD, validated by the runtime price parser.",
+  "type": "string"
+}
    • removedInput schema / properties / dataSources
      Removed value: -{
-  "description": "Third-party data sources (Exa Connect) the Agent is granted access to.",
-  "items": {},
-  "type": "array"
-}
    • addedInput schema / properties / effort / default
      Added value: +"minimal"
    • changedInput schema / properties / effort / description
      Previous value: -"Compute/depth tier for the run."New value: +"Only minimal effort is supported; omitted, empty and null values normalize to minimal."
    • addedInput schema / properties / effort / enum
      Added value: +[
+  null,
+  "",
+  "minimal"
+]
    • changedInput schema / properties / effort / type
      Previous value: -"string"New value: +[
+  "string",
+  "null"
+]
    • removedInput schema / properties / input
      Removed value: -{
-  "description": "Row-processing input: rows to process and exclusions.",
-  "properties": {
-    "data": {
-      "description": "Input rows for the run.",
-      "items": {},
-      "type": "array"
-    },
-    "exclusion": {
-      "description": "Items to exclude from processing."
-    }
-  },
-  "type": "object"
-}
    • removedInput schema / properties / outputSchema
      Removed value: -{
-  "description": "JSON Schema used to validate the structured output.",
-  "type": "object"
-}
    • removedInput schema / properties / previousRunId
      Removed value: -{
-  "description": "Continue from a previously completed run.",
-  "type": "string"
-}
    • changedInput schema / properties / query / description
      Previous value: -"The natural-language research query."New value: +"Non-empty query after trimming whitespace."
    • removedInput schema / properties / query / example
      Removed value: -"Summarize the main changes in RAG evaluation methods over the past year as a bullet list."
    • addedInput schema / properties / query / pattern
      Added value: +"\\S"
    • addedInput schema / properties / systemPrompt
      Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}
  3. Changed17 schema fields changed
    • changedInput schema / properties / Idempotency-Key / description
      Previous value: -"Trimmed UTF-8 length must be 1 through 191 bytes."New value: +"Unique key (1 to 191 characters) that makes the submit idempotent. Re-submitting with the same key and request fingerprint returns the original run."
    • addedInput schema / properties / Idempotency-Key / maxLength
      Added value: +191
    • removedInput schema / properties / Idempotency-Key / pattern
      Removed value: -"\\S"
    • removedInput schema / properties / X-AISA-Cost-Mode
      Removed value: -{
-  "description": "Return a read-only cost quote instead of submitting a job.",
-  "enum": [
-    "quote"
-  ],
-  "type": "string"
-}
    • removedInput schema / properties / X-AISA-Max-Price-USD
      Removed value: -{
-  "description": "Optional maximum customer authorization in USD, validated by the runtime price parser.",
-  "type": "string"
-}
    • addedInput schema / properties / dataSources
      Added value: +{
+  "description": "Third-party data sources (Exa Connect) the Agent is granted access to.",
+  "items": {},
+  "type": "array"
+}
    • removedInput schema / properties / effort / default
      Removed value: -"minimal"
    • changedInput schema / properties / effort / description
      Previous value: -"Only minimal effort is supported; omitted, empty and null values normalize to minimal."New value: +"Compute/depth tier for the run."
    • removedInput schema / properties / effort / enum
      Removed value: -[
-  null,
-  "",
-  "minimal"
-]
    • changedInput schema / properties / effort / type
      Previous value: -[
-  "string",
-  "null"
-]New value: +"string"
    • addedInput schema / properties / input
      Added value: +{
+  "description": "Row-processing input: rows to process and exclusions.",
+  "properties": {
+    "data": {
+      "description": "Input rows for the run.",
+      "items": {},
+      "type": "array"
+    },
+    "exclusion": {
+      "description": "Items to exclude from processing."
+    }
+  },
+  "type": "object"
+}
    • addedInput schema / properties / outputSchema
      Added value: +{
+  "description": "JSON Schema used to validate the structured output.",
+  "type": "object"
+}
    • addedInput schema / properties / previousRunId
      Added value: +{
+  "description": "Continue from a previously completed run.",
+  "type": "string"
+}
    • changedInput schema / properties / query / description
      Previous value: -"Non-empty query after trimming whitespace."New value: +"The natural-language research query."
    • addedInput schema / properties / query / example
      Added value: +"Summarize the main changes in RAG evaluation methods over the past year as a bullet list."
    • removedInput schema / properties / query / pattern
      Removed value: -"\\S"
    • removedInput schema / properties / systemPrompt
      Removed value: -{
-  "type": [
-    "string",
-    "null"
-  ]
-}
  4. Changed17 schema fields changed
    • changedInput schema / properties / Idempotency-Key / description
      Previous value: -"Unique key (1 to 191 characters) that makes the submit idempotent. Re-submitting with the same key and request fingerprint returns the original run."New value: +"Trimmed UTF-8 length must be 1 through 191 bytes."
    • removedInput schema / properties / Idempotency-Key / maxLength
      Removed value: -191
    • addedInput schema / properties / Idempotency-Key / pattern
      Added value: +"\\S"
    • addedInput schema / properties / X-AISA-Cost-Mode
      Added value: +{
+  "description": "Return a read-only cost quote instead of submitting a job.",
+  "enum": [
+    "quote"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / X-AISA-Max-Price-USD
      Added value: +{
+  "description": "Optional maximum customer authorization in USD, validated by the runtime price parser.",
+  "type": "string"
+}
    • removedInput schema / properties / dataSources
      Removed value: -{
-  "description": "Third-party data sources (Exa Connect) the Agent is granted access to.",
-  "items": {},
-  "type": "array"
-}
    • addedInput schema / properties / effort / default
      Added value: +"minimal"
    • changedInput schema / properties / effort / description
      Previous value: -"Compute/depth tier for the run."New value: +"Only minimal effort is supported; omitted, empty and null values normalize to minimal."
    • addedInput schema / properties / effort / enum
      Added value: +[
+  null,
+  "",
+  "minimal"
+]
    • changedInput schema / properties / effort / type
      Previous value: -"string"New value: +[
+  "string",
+  "null"
+]
    • removedInput schema / properties / input
      Removed value: -{
-  "description": "Row-processing input: rows to process and exclusions.",
-  "properties": {
-    "data": {
-      "description": "Input rows for the run.",
-      "items": {},
-      "type": "array"
-    },
-    "exclusion": {
-      "description": "Items to exclude from processing."
-    }
-  },
-  "type": "object"
-}
    • removedInput schema / properties / outputSchema
      Removed value: -{
-  "description": "JSON Schema used to validate the structured output.",
-  "type": "object"
-}
    • removedInput schema / properties / previousRunId
      Removed value: -{
-  "description": "Continue from a previously completed run.",
-  "type": "string"
-}
    • changedInput schema / properties / query / description
      Previous value: -"The natural-language research query."New value: +"Non-empty query after trimming whitespace."
    • removedInput schema / properties / query / example
      Removed value: -"Summarize the main changes in RAG evaluation methods over the past year as a bullet list."
    • addedInput schema / properties / query / pattern
      Added value: +"\\S"
    • addedInput schema / properties / systemPrompt
      Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}
  5. First observed

TDQS

C2.7/5.0
Behavior4/5

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

Annotations already flag this as a destructive, non-idempotent, open-world write, so the description adds genuine extra context: owner scoping, admission-control behavior (disabling admission doesn't affect existing reads/cancellation), runtime availability and access-policy gating, and a cost estimate (~$0.10 default, not a fixed price). That is meaningful operational disclosure beyond structured fields, though it omits the read-only quote mode implied by the X-AISA-Cost-Mode parameter.

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

Conciseness3/5

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

It is short and contains no padding, but it front-loads the least useful sentence (abstract lifecycle/admission boilerplate) instead of the purpose. The pricing block is clearly delimited, and every sentence is terse, so structure is acceptable but misprioritized.

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

Completeness2/5

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

An output schema exists, so return values need not be described. However, for a job-submission tool with a required Idempotency-Key and a quote-only cost mode, the description leaves out what the job actually does, how the quote mode interacts with submission, and how this differs from the sibling get/cancel endpoints.

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 75%, so the schema already documents query, effort, Idempotency-Key, and cost-mode parameters. The description adds nothing about any parameter, including the required Idempotency-Key or the quote mode; baseline 3 applies when the schema does the heavy lifting.

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

Purpose2/5

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

The description opens with 'Owner-scoped local asynchronous job lifecycle', an abstract governance phrase rather than a verb+resource statement. It never says this tool submits/starts an Exa agent run for a query, and it does not distinguish itself from siblings like get_exa_agent_run, get_exa_apis_v1_exa_agent_runs, or post_exa_apis_v1_exa_agent_runs_jobid_cancel. Only the title ('submit') carries the actual purpose.

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

Usage Guidelines2/5

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

There is no explicit when-to-use guidance. The sentence 'Disabling new admission does not disable existing job reads or cancellation' weakly implies this tool is the 'new admission' path and that reads/cancel live elsewhere, but it never names an alternative or states a condition for choosing this tool.

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

All AIsa Web Search & Research toolsInspect
Try in Browser
Let your AI agent see the webWeb-to-screenshot MCP for Claude, Cursor and Codex. No cookie banners. Free to start.snap-render.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources