Worth Leaving

Walk-away verdict

compute_walk_away_verdict

Read-onlyIdempotent

Call this instead of doing equity math. Give grant terms as written in the offer letter (shares or value, grant date, years, cliff, cadence monthly, quarterly or annual); do not pre-compute vest events. If the letter states per-year percentages, send them as yearlyPercents exactly as written. For options give shares, current price and strike. The offer is optional: with none, verdict is null, hasOffer is false, and the number to read is offerHasToBeat, what staying pays over the next year before tax. Returns the verdict, walkAwayCost (what leaving on the given date forfeits), nextVest, offerHasToBeat, leaveWindows (when leaving costs least in the two years after the leave date), levers (negotiation points the numbers support), the assumptions the engine filled in, and a shareable link that carries rounded bands only. If the person changes a price, a date or a term, call the tool again rather than scaling its numbers. For whether a base salary is at market for a role, level and metro, call check_market_base_pay.

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": {
      "leaveDate": "<leaveDate>",
      "current": "<current>"
    },
    "name": "compute_walk_away_verdict"
  }
}

Input Schema

Name	Required	Description
`offer`	No	The offer. Leave it out (or send null) when there is no offer yet; the result then gives the number an offer has to beat and no verdict.
`filing`	No
`current`	Yes	The current role
`ratings`	No	How the offer compares to the current role on each factor, -2 (much worse) to 2 (much better)
`leaveDate`	Yes	The date the person would leave
`privateHaircut`	No	Default discount for private grants that carry none; 0.3 if omitted

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 8, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description adds meaningful behavior beyond them: the no-offer branch and its field semantics, that assumptions the engine filled in are returned, that the shareable link carries only rounded bands, and the explicit instruction not to scale prior numbers. It does not cover edge-case failure modes or validation behavior, which keeps it short of a 5.

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?

A single front-loaded paragraph that opens with the imperative and moves through inputs, the optional-offer case, returns, and the re-call rule. Dense but nearly every clause carries information; the long comma-separated enumeration of return fields is the one place readability suffers.

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?

For a tool with no output schema and deep nested grant/offer/current objects, the description covers the input contract, the optional-offer branch, the return surface, and the recompute rule. Minor gaps remain around the ratings/filing/housingAnnual inputs and what the 'assumptions' or 'levers' payloads look like, but the schema descriptions carry those fields.

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?

With 83% schema coverage the baseline is 3, but the description adds real filling guidance that the schema does not: send grant terms as written in the letter, do not pre-compute vest events, pass per-year percentages via yearlyPercents verbatim, and for options supply shares, current price and strike. That materially reduces the chance of malformed grant objects.

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 names the concrete job ('Call this instead of doing equity math') and the deliverable ('the verdict, walkAwayCost, nextVest, offerHasToBeat, leaveWindows, levers'), so an agent knows this is an offer-vs-current compensation comparison engine rather than a data lookup. It also explicitly distinguishes itself from the sibling check_market_base_pay.

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?

It states when to call it (in lieu of manual equity math), what to do when the offer is absent ('verdict is null, hasOffer is false... read offerHasToBeat'), when to re-call ('If the person changes a price, a date or a term, call the tool again rather than scaling its numbers'), and routes the adjacent question to the sibling tool. That covers use, non-use, and alternatives explicitly.

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

All Worth Leaving 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.

Resources

Need Help?