Skip to main content
Glama

Get a price

get_estimate

PaisaLocal's installed price for a job, line by line, from its own Dallas-Fort Worth price list (the same quote paisalocal.com gives). Concrete needs length_ft, width_ft and a finish; a retaining wall needs length_ft, height_ft and a natural stone (e.g. Lueders Buff Chopped, Oklahoma Red Chopped, Granbury Stone). An outdoor kitchen needs length_ft (the total counter run in linear feet: 8-20, an L needs 10+, a U 15+), layout (straight, L or U), a natural stone for the outside of the island, an appliance package and a countertop slab (ask the homeowner; never pick one for them). If the reply asks for a stone, appliance package or countertop choice, ask the homeowner using the choices it lists and call again with their pick. Never call once per option to compare prices. When the reply has stoneOptions, show the homeowner every stone as its name linked to its photoUrl, so they can see each one before choosing. After pricing, link stonePhotoUrl next to the stone name. Returns estimate_id for request_site_visit and seeItInYourYardUrl: a paisalocal.com link where the homeowner uploads a photo of their yard and sees this job drawn onto it, and seeItInYourYardHowTo: the steps on that page. A photo shared in this chat cannot reach these tools, so after giving the price, offer the link with those steps in your own words, and tell the homeowner the photo goes on that page, not into this chat.

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": {
      "zip": "<zip>",
      "project_type": "<project_type>",
      "length_ft": "<length_ft>"
    },
    "name": "get_estimate"
  }
}

Input Schema

NameRequiredDescriptionDefault
useNoConcrete only: patio (default), driveway, sidewalk, walkway, slab, hot_tub (pad), trailer (RV/boat) or heavy (equipment)
zipYes5-digit US ZIP code of the job
stoneNoRetaining wall or outdoor kitchen: natural stone name
finishNoConcrete only, required: broom, salt, exposed or stamped (ask the homeowner; never pick one for them)
layoutNoOutdoor kitchen only, required: straight, L or U (ask the homeowner; never pick one for them)
width_ftNoConcrete only: width in feet
height_ftNoRetaining wall only: height in feet
length_ftYesLength in feet (outdoor kitchen: total counter run in linear feet)
appliancesNoOutdoor kitchen only, required: compact_chef (The Compact Chef), entertainer (The Entertainer's Setup), pitmaster (The Pitmaster Pro) or structure_only (no appliances). Ask the homeowner; only packages that fit the run are accepted
countertopNoOutdoor kitchen only, required: countertop slab name (ask the homeowner; never pick one for them)
project_typeYesconcrete | retaining-wall | outdoor-kitchen (curb-stone, french-drain: priced on paisalocal.com)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the annotations, the description discloses important behavior: it names returned fields such as estimate_id, seeItInYourYardUrl and seeItInYourYardHowTo, explains that missing stone/appliance/countertop choices require asking the homeowner and calling again, and warns that chat photos cannot reach these tools. This gives the agent a clear picture of the interaction flow and output handling.

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?

The description is front-loaded with purpose and then walks through project-type requirements before explaining return values and the photo-link follow-up. It is information-dense and mostly earns its length, though some repeated instructions (e.g., asking the homeowner and never choosing for them) could be tightened.

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?

For a complex 11-parameter pricing tool with no output schema, the description is complete: it explains required inputs by scenario, describes the returned estimate_id and visualization fields, and covers the follow-up action of offering the seeItInYourYard link with instructions. Nothing essential for correct invocation is obviously 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 description coverage is 100%, so the baseline is 3, but the description adds conditional requiredness across project types (e.g., concrete needs width_ft and finish; retaining wall needs height_ft and stone; outdoor kitchen needs layout, appliance package, stone and countertop). It also adds constraints such as the 8-20 linear-foot counter run and the L/U minimums, which are not fully captured in the schema alone.

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 immediately states that the tool returns PaisaLocal's installed price for a job, line by line, from its Dallas-Fort Worth price list. It also names concrete job types and the downstream estimate_id used by request_site_visit, making the tool's scope distinct from the sibling tools.

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?

The description gives detailed procedural guidance: it lists required inputs per project type, instructs the agent to ask the homeowner for missing choices, forbids calling once per option to compare prices, and says to offer the yard-visualization link after pricing. It lacks an explicit when-not-to-use statement or a direct comparison to find_contractor, which keeps it from a 5.

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.

Resources