Skip to main content
Glama

Estimate a PERM decision date

estimate_decision
Read-onlyIdempotent

When a pending PERM case is likely to be decided, with the range, the model and its caveats. Send a case number, or a filing date for a case in analyst review. It's an estimate from DOL's measured pace and makes no promise: show the caveats with the date. Example: {"filed":"2026-02-15"}.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "estimate_decision"
  }
}

Input Schema

NameRequiredDescriptionDefault
caseNoA PERM case number. Its own status and filing date are used. Example: G-100-26045-123456.
filedNoA filing date, for a case in analyst review, when there's no case number. Example: 2026-02-15.

Output Schema

NameRequiredDescriptionDefault
asOfYesThe date the data is true for, YYYY-MM-DD, when one applies.
dataYesThe answer, or found: false when no record matched.
pageYesThe page on permtracker.app that shows the same thing. Cite it.
sourceYesWho published the underlying records.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • addedInput schema / properties / case
      Added value: +{
      +  "description": "A PERM case number. Its own status and filing date are used. Example: G-100-26045-123456.",
      +  "maxLength": 40,
      +  "type": "string"
      +}
    • removedInput schema / properties / case_number
      Removed value: -{
      -  "description": "A PERM case number.",
      -  "maxLength": 40,
      -  "type": "string"
      -}
    • changedInput schema / properties / filed / description
      Previous value: -"Filing date, YYYY-MM-DD, when there's no case number."New value: +"A filing date, for a case in analyst review, when there's no case number. Example: 2026-02-15."
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "additionalProperties": false,
      +  "properties": {
      +    "asOf": {
      +      "description": "The date the data is true for, YYYY-MM-DD, when one applies.",
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    },
      +    "data": {
      +      "anyOf": [
      +        {
      +          "additionalProperties": {},
      +          "description": "When a pending PERM case is likely to be decided. An estimate from DOL's own pace: it makes no promise.",
      +          "properties": {
      +            "basis": {
      +              "description": "How the estimate was worked out, in a sentence.",
      +              "type": "string"
      +            },
      +            "caveats": {
      +              "description": "What the estimate can't know. Show them with the date.",
      +              "items": {
      +                "type": "string"
      +              },
      +              "type": "array"
      +            },
      +            "decisionDate": {
      +              "anyOf": [
      +                {
      +                  "description": "The day DOL decided the case, for the decided kind, as YYYY-MM-DD.",
      +                  "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
      +                  "type": "string"
      +                },
      +                {
      +                  "type": "null"
      +                }
      +              ]
      +            },
      +            "earliest": {
      +              "description": "The early end of the range, as YYYY-MM-DD.",
      +              "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
      +              "type": "string"
      +            },
      +            "estimatedDate": {
      +              "description": "The likeliest decision day, as YYYY-MM-DD.",
      +              "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
      +              "type": "string"
      +            },
      +            "filingDate": {
      +              "anyOf": [
      +                {
      +                  "description": "The filing date the estimate is for, as YYYY-MM-DD.",
      +                  "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
      +                  "type": "string"
      +                },
      +                {
      +                  "type": "null"
      +                }
      +              ]
      +            },
      +            "kind": {
      +              "description": "date: an estimated day with a range. no-date: the case is past every model's reach, with a note. none: no model can give a defensible date. decided: the case already has a decision.",
      +              "enum": [
      +                "date",
      +                "no-date",
      +                "none",
      +                "decided"
      +              ],
      +              "type": "string"
      +            },
      +            "latest": {
      +              "description": "The late end of the range, as YYYY-MM-DD.",
      +              "pattern": "^\\d{4}-\\d{2}-\\d{2}$",
      +              "type": "string"
      +            },
      +            "model": {
      +              "description": "The model that produced the estimate, by name.",
      +              "type": "string"
      +            },
      +            "note": {
      +              "description": "Why there is no date, for the no-date and none kinds.",
      +              "type": "string"
      +            },
      +            "pendingCasesAhead": {
      +              "anyOf": [
      +                {
      +                  "maximum": 9007199254740991,
      +                  "minimum": -9007199254740991,
      +                  "type": "integer"
      +                },
      +                {
      +                  "type": "null"
      +                }
      +              ],
      +              "description": "Pending PERM cases filed before this one."
      +            },
      +            "status": {
      +              "description": "The status the estimate assumed, e.g. ANALYST REVIEW.",
      +              "type": [
      +                "string",
      +                "null"
      +              ]
      +            },
      +            "waitedDays": {
      +              "description": "Days the case has waited, for the no-date kind.",
      +              "maximum": 9007199254740991,
      +              "minimum": -9007199254740991,
      +              "type": "integer"
      +            }
      +          },
      +          "required": [
      +            "kind"
      +          ],
      +          "type": "object"
      +        },
      +        {
      +          "additionalProperties": false,
      +          "description": "No such record. Say so; don't retry the same call.",
      +          "properties": {
      +            "found": {
      +              "const": false,
      +              "description": "False: no record matched.",
      +              "type": "boolean"
      +            },
      +            "message": {
      +              "description": "What wasn't found and what to try, in a sentence.",
      +              "type": "string"
      +            }
      +          },
      +          "required": [
      +            "found",
      +            "message"
      +          ],
      +          "type": "object"
      +        }
      +      ],
      +      "description": "The answer, or found: false when no record matched."
      +    },
      +    "page": {
      +      "description": "The page on permtracker.app that shows the same thing. Cite it.",
      +      "type": "string"
      +    },
      +    "source": {
      +      "description": "Who published the underlying records.",
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "source",
      +    "asOf",
      +    "page",
      +    "data"
      +  ],
      +  "type": "object"
      +}
  2. First observed

TDQS

A4/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so safety is covered. The description adds materially new behavior: the value is a model estimate based on DOL's measured pace, it carries caveats, and the agent is told to surface those caveats alongside the date rather than presenting it as a promise.

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?

Three tight sentences plus an example, with the input-routing rule and the caveat instruction prominent. The opening is a subordinate clause rather than a direct statement of what the tool does, which is slightly less front-loaded than ideal.

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?

With an output schema present, the return values need not be enumerated, and the description still says what comes back (date, range, model, caveats) and how to present it. Optional-parameter logic and the estimate's uncertain nature are both covered, leaving nothing an agent needs missing.

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 coverage is 100% and both parameters already carry descriptions, so the baseline of 3 applies. The description reinforces the "analyst review / no case number" condition for `filed`, but adds no format or constraint detail beyond the schema.

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

Purpose4/5

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

"When a pending PERM case is likely to be decided, with the range, the model and its caveats" states a specific resource (pending PERM case) and the exact output shape (estimate + range + model + caveats), which separates it from get_case or find_cases. It stops short of naming a sibling or using a clean leading verb, which keeps it at 4 rather than 5.

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?

"Send a case number, or a filing date for a case in analyst review" gives a clear routing rule between the two inputs and the condition selecting the second. It does not state when not to use this tool (e.g., for already-decided cases, defer to get_case), so no exclusion guidance.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.