Skip to main content
Glama

SNHP — free negotiation math + agent memory

Negotiate a bundle — logroll linked issues

negotiate_bundle
Read-only

Negotiate several linked issues at once by logrolling — free, no account or key needed.

USE THIS WHEN: a deal has more than one issue on the table and they trade off — a job offer (base + equity + signing), a SaaS contract (price + seats + term + SLA), any package deal. It concedes on the issues you care about LESS (and the other side cares about MORE) to win the ones you care about most — a trade that beats splitting every issue down the middle. For a single PRICE, use negotiate instead.

Provide issues: a list of {"name", "options" (the choices), "my_utility" (how good each option is to YOU — one number per option, any scale), "their_utility" (how good each option is to THEM — their preference direction)}. Optionally my_priorities ({issue_name: weight}, how much each issue matters to you) and their_offers (their packages so far as {issue_name: option}, oldest first — this is what lets it INFER their priorities). Returns {action, recommended_offer (issue -> option), message, my_utility, their_expected_utility, inferred_their_priorities, trade_logic, fit, confidence, acceptance_probability}.

Validated (separately from the single-issue +12%): returns a Pareto-efficient package that beats naive "split-every-issue-down-the-middle" bargaining by ~40% joint surplus (300 random 4-issue profiles). HONEST CAVEAT: the priority INFERENCE layered on top is weak (recovery r≈0.3) and currently adds only ~1% (and can be slightly NEGATIVE against some opponents) over the same engine run with no inference — so the proven value today is the efficient-package search, not (yet) the logrolling edge.

Optional timing refinement: pass rounds_left (bargaining rounds remaining) with compute_ms > 0 to spend that many ms of Monte-Carlo rollouts choosing WHICH package to hold for as the other side concedes over the rounds — a firmer package closes later (discounted) than a generous one. 0 = the instant closed-form package; the reply then carries a compute block. Modest by design (never worse than the closed form in-model; helps on a minority of deals).

Example: a SaaS contract — you most want a low price_per_seat, can flex on seats/term/SLA. negotiate_bundle(issues=[ {"name":"price_per_seat","options":["$50","$40","$30"],"my_utility":[0,0.5,1],"their_utility":[1,0.5,0]}, {"name":"sla","options":["99%","99.9%"],"my_utility":[0,1],"their_utility":[1,0]} ...], my_priorities={"price_per_seat":0.55,"sla":0.1,...}, their_offers=[...]) -> a full package that gives ground on SLA to hold the price.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
issuesYesOne dict per issue: {name, options (the choices), my_utility (value of each option to YOU), their_utility (value to THEM)} — utilities are one number per option, any scale.
my_batnaNoYour best alternative to no deal, as a utility fraction in [0,1] (default 0.40); the returned package is guaranteed to beat it.
compute_msNoEXPERIMENTAL. Milliseconds of rollouts to choose WHICH package to hold as they concede; 0 = instant closed-form package.
rounds_leftNoBargaining rounds remaining (used with compute_ms for the timing tier; default 8).
their_offersNoPackages the other side has tabled, oldest first, each as {issue_name: chosen_option} — lets it infer their priorities.
my_prioritiesNo{issue_name: weight} — how much each issue matters to you (any scale). Optional.
their_batna_estimateNoYour estimate of the other side's BATNA, [0,1] (default 0.40).

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
fitNo
errorNo
actionNo
computeNo
messageNo
confidenceNo
my_utilityNo
trade_logicNo
recommended_offerNo
acceptance_probabilityNo
their_expected_utilityNo
inferred_their_prioritiesNo

TDQS

A4.9/5.0
Behavior5/5

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

The description details behavioral traits: free, no account needed, returns Pareto-efficient package, includes honest caveat about priority inference weakness, and explains optional timing refinement. It does not contradict annotations (readOnlyHint is reasonable for a computation tool).

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 lengthy but well-organized into sections (usage, validation, caveats, example). It is front-loaded with purpose and usage. Every sentence adds value, though could be slightly more concise.

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?

Given the complexity of multi-issue negotiation, the description is complete: covers purpose, usage, parameters, output, validation results, caveats, and an example. The output schema exists, but description still adds necessary trade-off logic context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Despite 100% schema coverage, the description adds significant meaning beyond schema: explains utility scales, issue structure, optional parameters like my_priorities and their_offers, and provides a detailed example. It fully compensates for any schema brevity.

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 clearly states the tool's purpose: 'Negotiate several linked issues at once by logrolling'. It uses specific verbs and resources, and distinguishes from sibling tool 'negotiate' which is for single price issues.

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?

The description provides explicit when-to-use guidance: 'USE THIS WHEN: a deal has more than one issue on the table and they trade off... For a single PRICE, use negotiate instead.' It also gives examples like job offers and SaaS contracts.

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.

TDQS

A4/5.0
Disambiguation4/5

Most tools have distinct purposes (e.g., auctions, negotiation, pricing, matching, memory). However, negotiate/session_advise and negotiate_bundle/session_bundle overlap in functionality, differing only in payment tier, which could cause confusion.

Naming Consistency4/5

Tool names generally follow a verb_noun pattern in snake_case. 'negotiate' is a lone verb without a noun, but overall the convention is consistent and predictable.

Tool Count4/5

15 tools cover a broad domain of negotiation, auctions, pricing, matching, and memory. While slightly on the higher side, each tool serves a clear purpose and the count is reasonable for the scope.

Completeness4/5

The tool surface covers key negotiation scenarios (single/multi-issue, free/paid, auctions, clearance pricing, stable matching) and adds memory persistence. Minor gap: no explicit tool for managing user preferences or profiles.