GISDB

curate_portfolio_selection

Idempotent

Interactively curate a staged portfolio selection in Chat / MCP: add new parcels, remove sold or NNN properties, toggle selection, set Primary Residence / Homestead HQ, or execute natural language instructions with TypeSafe System One (Jev). Recalculates selected parcel counts, total market value, and estimated annual tax recovery in real-time.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "staged_properties": "<staged_properties>"
    },
    "name": "curate_portfolio_selection"
  }
}

Input Schema

Name	Required	Description
`action`	No	Curation action: 'remove', 'add', 'set_homestead', 'toggle', or 'auto' (default: 'auto')
`reason`	No	Reason for exclusion or modification (e.g. 'under contract to sell', 'NNN lease')
`staging_id`	No	Optional staging identifier
`client_name`	No	Optional client name
`staged_properties`	Yes	Array of staged property objects from previous staging/curation turn
`address_or_parcel_id`	No	Target street address, parcel ID, or street name token (e.g. '4006 Brock Rd' or 'Brock Rd')
`conversational_instruction`	No	Natural language instruction from user in chat (e.g. 'Remove Brock Rd because we are selling it next week, keep the rest')

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 6, 2026

TDQS

A3.6/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=true, and openWorldHint=false, so the safety profile is largely covered. The description adds genuine value by stating that counts, total market value, and estimated annual tax recovery are recalculated in real-time, and that operations apply to a staged selection rather than live records. It does not say whether removals are reversible or whether the staging state persists between turns.

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?

Two sentences, front-loaded with the core action and then the supported operations, with no filler. Some internal jargon ('TypeSafe System One (Jev)', 'Homestead HQ') is noise an external agent cannot act on, but it does not obscure the instructions.

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 7 parameters all documented in the schema, no output schema, and annotations covering safety, the description supplies the remaining needed context: what state it operates on (staged properties from a prior turn) and what gets recomputed. The main gap is the ordering relationship with stage_portfolio_selection, which an agent must infer.

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; every parameter including the action enum and its examples is already documented in the schema. The description's action list largely mirrors the enum and its 'NNN lease' / 'sold' examples duplicate the reason parameter's own example, adding little meaning beyond the structured fields.

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?

The description names a specific verb and resource ('curate a staged portfolio selection') and enumerates the concrete operations it supports (add, remove, toggle, set homestead, natural-language auto mode). It clearly distinguishes itself from the audit_* siblings by being an interactive curation step, though it never names stage_portfolio_selection, which is the closest neighbor.

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?

It gives clear usage context per action ('add new parcels, remove sold or NNN properties... set Primary Residence / Homestead HQ, or execute natural language instructions'), so an agent knows which scenario maps to which mode. It stops short of explicit when-not guidance, such as when to prefer stage_portfolio_selection first or when to use 'auto' versus an explicit action.

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

All GISDB 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.