Skip to main content
Glama

elc-partnership-builder

by io.engineeringleaders

Customize a package: toggle line items, recompute the total

customize_package
Read-onlyIdempotent

The conversational toggle board. Pass the preset and the item ids currently ON; returns the recomputed total (never trust your own arithmetic — this is the authoritative price), every selected item with its price, and what else this tier could add. Items marked foundation anchor the package; advise keeping them. Call again after every change the visitor asks for. Next: request_offer.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
seatsNoStarter only: how many people they are enrolling. Starter is priced per seat with volume bands, so ALWAYS ask for a headcount before quoting it — the bundle price is only the 3-seat entry.
contextYesExplain why you are calling this tool and how it fits into the user's overall goal. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include sensitive information such as credentials, passwords, or personal data. Example (20 words): "Searching across the organization's repositories to find all open issues related to performance complaints and latency issues for team prioritization."
item_idsYesItem ids currently toggled ON (from match_package default_item_ids, plus/minus changes)
preset_idYesThe package being customized

TDQS

A4.5/5.0
Behavior5/5

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

Beyond the readOnly/idempotent annotations, the description discloses that the tool is the authoritative price source and warns against doing own arithmetic, explains the return contents (total, selected items with prices, addable items), and gives guidance about foundation items. It also says to call again after every change, reinforcing idempotent stateless behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four tight sentences with no filler. The purpose is front-loaded, and each sentence adds value: invocation, authoritative output, foundation-item guidance, and call frequency/next step.

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 no output schema, the description adequately explains what will be returned and how to interpret it. It also covers when to call, what to pass, and what to advise about foundation items, making it complete for an agent to invoke correctly.

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% and each parameter already has substantial detail, including the seats headcount warning and item_ids provenance. The description only restates 'pass the preset and the item ids currently ON' without adding new parameter-level meaning, so the baseline 3 applies.

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?

States a specific verb and resource: customize a package by toggling line items and recomputing the authoritative total. It clearly distinguishes itself from related tools by describing this as the conversational toggle board that operates on currently-ON item IDs and hands off to request_offer next.

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?

Provides clear context: call it after every visitor change, pass the preset and currently-ON item IDs, and use its computed total as authoritative. It also routes the workflow forward with 'Next: request_offer.' It does not explicitly name alternatives or exclusions, but the intended usage is well implied.

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

All elc-partnership-builder toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.3/5.0
Disambiguation4/5

Most tools map cleanly to distinct funnel stages: qualify, match, customize, fit to budget, timeline, business case, offer, and booking. The only mild ambiguities are between match_package and fit_to_budget (both compose packages from budget input) and between request_offer and book_intro_call (both are conversion endpoints), though the descriptions do draw clear boundaries.

Naming Consistency5/5

All nine tool names follow the same verb_noun snake_case convention (get_partnership_options, customize_package, build_business_case, request_offer). get_more_tools is semantically a meta-tool, but it still follows the naming pattern, so there is no stylistic inconsistency.

Tool Count4/5

Nine tools is a well-scoped size for a guided sales-funnel server, and each domain tool corresponds to a meaningful workflow step. get_more_tools is a generic meta-tool that doesn't fully earn its place, which keeps this from a perfect score.

Completeness4/5

The toolset covers the full partnership lifecycle from qualification and package matching through customization, budgeting, timeline design, business-case generation, and final offer/booking. Minor gaps exist, such as no explicit package-catalog listing tool outside the matching flow and no direct handling of the individual-mentor path, but these are workaroundable or out of scope.

Resources