Skip to main content
Glama

Tallyho

Find a plumber

find
Read-only

Find plumbers for a job in San Francisco, Oakland, Berkeley and the Tri-Valley (Danville, San Ramon, Dublin, Pleasanton, Livermore), ranked by the chance they keep every promise that matters for it: take the job, have a slot in the window, quote within budget, arrive on time, hold the quote, finish, no upsell. Only job.location.zip is required; add system, issue, urgency, window and price_ceiling_cents for a sharper answer. Each candidate has a likelihood per promise with n (the evidence behind it), an 80% interval and freshness, the joint likelihood, and its CSLB license check. n=0 is Tallyho's starting estimate, not a measurement. Free; never contacts a business. Next: book a candidate with this find_id.

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": {
      "job": "<job>"
    },
    "name": "find"
  }
}

Input Schema

NameRequiredDescriptionDefault
jobYes
testNoMark this search and anything booked from it as a test; test rows never change a likelihood.
limitNo
promisesNoWhich promises matter for this job. Default: every promise the spec lets Tallyho judge.

Output Schema

NameRequiredDescriptionDefault
jobYes
notesYes
find_idYes
coverageYes
candidatesYes
environmentYes
contract_versionYes
promises_in_scopeYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description reinforces this with "Free; never contacts a business" — useful since it rules out outreach side effects. It also discloses an important interpretive caveat ("n=0 is Tallyho's starting estimate, not a measurement") and describes the per-candidate evidence structure. However, it adds little on rate limits, result caps, or failure modes beyond the n=0 note.

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?

Purpose is front-loaded and the paragraph is dense with substance rather than filler, though the geography list appears twice (opening and inside the zip hint) and the promise enumeration makes it run-on. Slightly tighter phrasing would improve scanability without losing information.

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 read-only search with a rich nested schema and an output schema, the description covers what is needed: required input, ranking behavior, the meaning of the returned evidence fields, the license check, and the handoff to book. Nothing an agent needs to call it correctly 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?

At 50% schema coverage the description must carry weight, and it does: it names the required path (job.location.zip) and lists which optional fields sharpen results (system, issue, urgency, window, price_ceiling_cents). It omits max_service_call_cents, promises, limit, test and brand, so an agent still has to read the schema for those.

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?

Opens with a specific verb and resource ("Find plumbers for a job") plus an explicit service area, then states the ranking criterion (chance they keep every promise). The closing "Next: book a candidate with this find_id" also distinguishes it from the sibling book tool.

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?

Explicitly states the minimum viable call ("Only job.location.zip is required") and why an agent would add optional parameters ("for a sharper answer"), which is genuine selection guidance. It stops short of naming when-not-to-use conditions or contrasting directly with status/report.

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