Skip to main content
Glama

AI Applyd

by com.aiapplyd
OverviewDiscussionsAdmin

Approve or Reject Applications

aiapplyd_review_application
Destructive

Act on the user's applications. decision "approve" submits each waiting application on the employer's hiring system under the user's name: it spends one of their applications per job and cannot be undone. "reject" skips it: nothing is sent and nothing is spent. "cancel" stops one that is still queued or preparing. "refine" rewrites its resume or cover letter from instructions (document_type and instructions; uses AI credits). "re_prepare" builds its documents again (optional steps). "set_stage" records how it is going (stage). Pass up to 25 application_ids from aiapplyd_get_applications. Only approve on the user's explicit go-ahead, such as a "yes" to a specific application. On a timeout or an error, call aiapplyd_get_applications before retrying; an approve that already went through is reported as already approved. Do not use it for matches with no application yet; use aiapplyd_apply or aiapplyd_triage_matches. Next: aiapplyd_get_applications to follow the submissions.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
stageNoFor set_stage: applied, callback, phone_screen, interview, offered, rejected or no_response.
stepsNoFor re_prepare: the steps to run again. Omit to run every step that is out of date.
decisionYes"approve" submits the application to the employer and cannot be undone. "reject" skips it and sends nothing. "cancel" stops a queued one. "refine" rewrites a document (needs document_type and instructions). "re_prepare" builds its documents again. "set_stage" records the stage (needs stage).
instructionsNoFor refine: what to change, in the user's own words (up to 2,000 characters).
document_typeNoFor refine: "resume" or "cover_letter".
application_idsYesApplication ids to act on, 1 to 25 (e.g. [1550, 1551]), from aiapplyd_get_applications

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultsYes
decisionYes
attemptedYes
succeededYes
notConfirmedYesTrue when the user declined the confirmation prompt and nothing was sent.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed10 schema fields changed
    • removedInput schema / additionalProperties
      Removed value: -false
    • addedInput schema / properties / application_ids / items / maximum
      Added value: +9007199254740991
    • addedOutput schema / properties / results / items / properties / applicationStage / anyOf
      Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
    • removedOutput schema / properties / results / items / properties / applicationStage / type
      Removed value: -[
-  "string",
-  "null"
-]
    • addedOutput schema / properties / results / items / properties / reason / anyOf
      Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
    • removedOutput schema / properties / results / items / properties / reason / type
      Removed value: -[
-  "string",
-  "null"
-]
    • addedOutput schema / properties / results / items / properties / refinedContent / anyOf
      Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
    • removedOutput schema / properties / results / items / properties / refinedContent / type
      Removed value: -[
-  "string",
-  "null"
-]
    • addedOutput schema / properties / results / items / properties / status / anyOf
      Added value: +[
+  {
+    "type": "string"
+  },
+  {
+    "type": "null"
+  }
+]
    • removedOutput schema / properties / results / items / properties / status / type
      Removed value: -[
-  "string",
-  "null"
-]
  2. Changed16 schema fields changed
    • addedInput schema / properties / application_ids / items / exclusiveMinimum
      Added value: +0
    • changedInput schema / properties / application_ids / items / type
      Previous value: -"number"New value: +"integer"
    • changedInput schema / properties / decision / description
      Previous value: -"\"approve\" submits the application to the employer and cannot be undone. \"reject\" skips it and sends nothing."New value: +"\"approve\" submits the application to the employer and cannot be undone. \"reject\" skips it and sends nothing. \"cancel\" stops a queued one. \"refine\" rewrites a document (needs document_type and instructions). \"re_prepare\" builds its documents again. \"set_stage\" records the stage (needs stage)."
    • changedInput schema / properties / decision / enum
      Previous value: -[
-  "approve",
-  "reject"
-]New value: +[
+  "approve",
+  "reject",
+  "cancel",
+  "refine",
+  "re_prepare",
+  "set_stage"
+]
    • addedInput schema / properties / document_type
      Added value: +{
+  "description": "For refine: \"resume\" or \"cover_letter\".",
+  "enum": [
+    "resume",
+    "cover_letter"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / instructions
      Added value: +{
+  "description": "For refine: what to change, in the user's own words (up to 2,000 characters).",
+  "maxLength": 2000,
+  "type": "string"
+}
    • addedInput schema / properties / stage
      Added value: +{
+  "description": "For set_stage: applied, callback, phone_screen, interview, offered, rejected or no_response.",
+  "enum": [
+    "applied",
+    "callback",
+    "phone_screen",
+    "interview",
+    "offered",
+    "rejected",
+    "no_response"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / steps
      Added value: +{
+  "description": "For re_prepare: the steps to run again. Omit to run every step that is out of date.",
+  "items": {
+    "enum": [
+      "quality_gate",
+      "company_intel",
+      "tailor_resume",
+      "translate",
+      "cover_letter"
+    ],
+    "type": "string"
+  },
+  "type": "array"
+}
    • changedOutput schema / properties / decision / enum
      Previous value: -[
-  "approve",
-  "reject"
-]New value: +[
+  "approve",
+  "reject",
+  "cancel",
+  "refine",
+  "re_prepare",
+  "set_stage"
+]
    • addedOutput schema / properties / notConfirmed
      Added value: +{
+  "description": "True when the user declined the confirmation prompt and nothing was sent.",
+  "type": "boolean"
+}
    • addedOutput schema / properties / results / items / properties / applicationStage
      Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}
    • addedOutput schema / properties / results / items / properties / reason / description
      Added value: +"Machine reason when ok is false, or \"already_approved\" for an approve that had already gone through."
    • addedOutput schema / properties / results / items / properties / refinedContent
      Added value: +{
+  "type": [
+    "string",
+    "null"
+  ]
+}
    • addedOutput schema / properties / results / items / properties / status / description
      Added value: +"Our own record after the action. Never proof the employer received it."
    • changedOutput schema / properties / results / items / required
      Previous value: -[
-  "applicationId",
-  "ok",
-  "status",
-  "reason",
-  "trackingUrl"
-]New value: +[
+  "applicationId",
+  "ok",
+  "status",
+  "reason",
+  "refinedContent",
+  "applicationStage",
+  "trackingUrl"
+]
    • changedOutput schema / required
      Previous value: -[
-  "decision",
-  "results",
-  "succeeded",
-  "attempted"
-]New value: +[
+  "decision",
+  "results",
+  "succeeded",
+  "attempted",
+  "notConfirmed"
+]
  3. Added

TDQS

A4.9/5.0
Behavior5/5

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

Annotations provide destructiveHint=true and idempotentHint=false, and the description richly elaborates on those: 'approve' 'spends one of their applications per job and cannot be undone', 'reject' sends and spends nothing, 'refine' 'uses AI credits', and a retried approve that already went through 'is reported as already approved'. This adds meaningful behavioral context beyond the annotations without contradicting them.

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?

The description is long but every sentence earns its place. It front-loads the core action and decision inventory, then layers constraints (id source and cap, consent rule, timeout recovery), exclusions, and the follow-up call. For a six-mode tool with error handling and sibling routing, this density is appropriate with zero fluff.

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

Completeness5/5

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 no prose explanation. The description covers everything needed for safe invocation: all six behaviors, the decision-to-parameter coupling, id sourcing and limits, the explicit-go-ahead consent rule, timeout/error handling, when-not-to-use with named alternatives, and the next step ('aiapplyd_get_applications to follow the submissions'). Nothing an agent needs is missing.

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 baseline is 3, but the description adds real meaning beyond the schema: it couples decisions to their required parameters ('refine' needs document_type and instructions, 'set_stage' needs stage, 're_prepare' takes optional steps), caps application_ids at 25, and specifies that ids come from aiapplyd_get_applications. This explains the interplay between parameters that the schema's per-field descriptions do not.

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 clear verb and resource ('Act on the user's applications') and then enumerates each decision mode ('approve', 'reject', 'cancel', 'refine', 're_prepare', 'set_stage') with its specific effect. It also distinguishes itself from siblings by naming aiapplyd_apply and aiapplyd_triage_matches as the tools for matches with no application yet.

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?

Provides explicit when-to-use guidance: pass up to 25 ids 'from aiapplyd_get_applications' and only approve 'on the user's explicit go-ahead'. Explicitly states when not to use it ('Do not use it for matches with no application yet; use aiapplyd_apply or aiapplyd_triage_matches') and gives recovery guidance for timeouts and errors. This is full when/when-not/alternatives coverage.

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

All AI Applyd toolsInspect
Try in Browser
Give agents eyes on the webHosted screenshot MCP. Send a URL, get a pixel-perfect image. $0.002 per grab. Works with Claude, Cursor, and Codex.grabbit.liveAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources