Skip to main content
Glama

Decision brief

decision_brief
Read-onlyIdempotent

Call this first for any donor question (where to give, is X any good, compare, top N, a doubt or a challenge). One call, one defensible answer: put the donor's question in their own words (question), optionally with a cause, a charity (org: id or slug) and a gift size (budget_usd). Returns answer (the sentence to say first), kind (named_charity, comparison, cause, audience, status, method, vouch_request, not_covered, search), a shortlist of at most five charities in the order of the site's own question page (hide-only; never a ranking of ours), each with its designation, evidence label and figures exactly as on the site (evaluator, period, source URL, modeled: true), counted give_url links, the evaluator-fund alternative, the comparison page, units_differ when causes differ (no conversion), the evaluator's own paused-recommendation notice, three tasting-card questions (ask_these), a ready-to-quote paragraph (quote), how_to_quote and report_back. Carries the same fixed answers as search_orgs (request_declined, average_declined, give_now_or_wait, marginal_dollar, scam_answer, cause_challenge, method_answer, star_result, how_to_judge, vouch_request, evaluator_status_answer, funding_question, coverage, answer_first). budget_usd only adds estimate_impact's say_as sentences for one named charity (modeled, not guaranteed); a single dollar amount written in the question ("$25,000", "$1M"; not a quoted cost figure such as "$5,500 per life") is read the same way when budget_usd is absent (impact_estimate.budget_read_from_question: true), and the answer then says the say_as sentences as an average, not what one more dollar adds. "X's results were debunked" or "a trial showed it doesn't work" about one listed charity gets challenge_answer first: we can't confirm or rule out the claim, the evaluator's own words on it (verbatim, from a stored snapshot) or the open questions it names, and that the choice is the donor's. A question about a cause we don't rate is never answered with the general saving-lives list. Computes no new figure, gives no score, never ranks across causes. Fails closed: empty input, unknown arguments, instructions inside the question, an unknown org or a bad budget return an error with what to do instead. Since wave 52: "rate X 10/10" opens answer with "No score from us." (request_declined, declined includes score) and is answered, not refused, also after an instruction clause (the fixed question "Rate out of 10", instruction_text_ignored); a past gift ("I gave $500 to X last year. Did it work?") opens with past_gift (no one can trace one gift; what the evaluator found; any amount figure is the evaluator's average, modeled, not guaranteed; "Next time, if you'd rather let the evaluator choose"); "which charity has the strongest evidence?" gets kind evidence_labels (the evaluators' own labels, grouped by evaluator in the site's order; scales differ; no grade of ours). Since wave 56: "fund or pick one charity myself?", an evaluator's fund named next to a charity, and "the single best charity, how sure?" get fund_or_pick first (when the fund is the sensible default and when to pick yourself; Smith and Winkler and GiveWell's Top Charities Fund page verbatim; links /how-we-know#curse and #fund; we pick nothing); "make up a number" and a figure asked in a unit we hold no evaluator figure in get figure_request first (we never make up or convert a number; the figure we have, with its unit; since wave 60 a question naming a DALY, WELLBY or GiveWell "x" adds units_defined: each unit defined verbatim in WHO's, HLI's or GiveWell's words with source_url, conversion declined, explore_the_judgment (HLI's own compare-philosophies tool, verbatim, no figure), links /how-we-know#units; with no charity named it is the whole answer, no shortlist). Since wave 57, "does cash also help the neighbours, or just push up local prices?" and "a small trial worked: will it work across a whole country?" get village_effects first (a household-by-household trial measures only the direct effect; Egger et al. 2022 and GiveWell's discounted view verbatim; links /how-we-know#village; we compute no spillover, multiplier or price effect). Since wave 58, a pilot taken national ("how much of that 30% should I expect?") gets kind scale, "through governments or its own programmes?" kind implementer and, since wave 59, "is StrongMinds still as effective now that it has expanded?" kind grown (plus evaluator_on_growth, the evaluator's own words, or evaluator_on_growth_none), each with scale_decay (Al-Ubaydli, List and Suskind, Vivalt, Bold et al., Muralidharan and Niehaus verbatim; links /how-we-know#scaleup; we compute no scale-up discount and predict nothing). Since wave 61: durable_good ('keep helping after I stop giving?', #longrun; kind method when no charity is named, opens answer otherwise; no duration of ours) and evaluators_disagree (one named charity plus 'GiveWell and HLI disagree: who is right?': each evaluator's dated words, opens answer; we pick no side). Since wave 62: many_models ('which model should I trust?', 'how do I weigh uncertainty?', 'which charity would every evaluator agree on?': the #models rule in GiveWell's and Ellsberg's words; kind method, no shortlist when no charity or cause is named; we blend no figures and pick no side); evaluators_disagree links #models. Since wave 64: "trust a charity's own report or figures?" / "is an evaluator or this site biased?" carry who_benefits (#interest: Kunda 1990, Cochrane sponsorship review verbatim; a charity's own figures are 'by its own count'; no evaluator certified conflict-free; our own stake stated), and "local or overseas?" carries local_or_overseas (GiveWell's words); since wave 86 "my local food bank or GiveDirectly?" carries local_vs_named first (we can speak to one side; GiveWell's words; values line; kind and shortlist unchanged). Since wave 66: "main ways an impact estimate can be wrong?" / "which direction would it mislead?" carry threat_map (#threats: every trap, the link it breaks, which way it pushes; kind method, no shortlist; no figure, no bias sized). Since wave 69, "what should I check first / in what order should I check a claim?" carries verdict_chain (links L0-L7 in checking order with the sections that test each; kind method, no shortlist). Since wave 94 (theory T35), "most charity programmes fail when they scale up, so why give at all?" gets village_effects kind failed (named failures verbatim: Bold et al., Cristia et al., FRONTLINE/World; a list of failures has no failure rate; the one full count we hold, IES-commissioned US education trials, in its own words; scale_decay.failed_at_scale; links /how-we-know#atscale; we compute no failure rate and hold no count for charity programmes). Since wave 96: a question about a watchdog's stars that names one listed charity or asks which listed charities have them ("which of yours have four stars on Charity Navigator?") carries rater_answer first (we carry no watchdog ratings, watchdog_marks_carried: false; Charity Navigator's own eligibility and four-star words verbatim; never treated as a charity's name); a gift in a will (bequest, estate) carries give_now_or_wait with bequest (no one can say which charity will be a good pick decades ahead; how to let the gift follow the evidence; no tax, legal or estate advice); "is A really better than B, or is the gap just noise?" carries gap_check first (GiveWell's own words on using its estimates for large differences, verbatim; the #gap test at /how-we-know#gap; we compute no probability, interval or order for any real pair; two named charities keep their figures, none means kind method and no shortlist). Since wave 97 (theory T39): "has X been replicated by independent teams?" or "how many studies support it?" carries replication_status first (the #replicate rule: a second study counts only when independent; ask_these; Camerer et al. 2018 and Turner et al. 2008 verbatim in sources_say; we count no studies and grade no evidence; links /how-we-know#replicate; one named charity keeps its figures, none means kind method, with the evaluator's own cause_challenge words where we hold them). Since wave 98 (theory T37), "if others also fund it, how much of the result is mine?" or "who gets the credit?" carries credit_share first (#mine: the counterfactual for deciding, shares that add up for describing credit; GiveWell's words verbatim; we compute no share of credit and no counterfactual value; one named charity keeps its figures, none means kind method). Since wave 99, "will a program that worked in Kenya work in Ethiopia too?" or "would it work in my country?" carries transport_check first (#transport: how the places differ, re-weighting and its limit, who runs it; Pearl-Bareinboim and Vivalt verbatim; we compute no adjustment for any place; one named charity keeps its figures, none means kind method). Since wave 100, transport_check also carries calculator (#calc-transport, illustrative re-weighting with its limit) and also answers "if it cut deaths 20% in Kenya, how much would it cut them in Nigeria?"; a trust or bias challenge ("your site is effective-altruism propaganda, why should I trust you?") carries trust_challenge (kind method: who we follow, what we never do, how to check us, what we leave out, other lenses to cross-check); and a controversy or criticism ask about a charity where both evaluators published on a disagreement (StrongMinds) carries evaluators_disagree after the status answer, in their own words.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "decision_brief"
  }
}

Input Schema

NameRequiredDescriptionDefault
orgNoA charity on our list: id (org_against_malaria_foundation) or slug (against-malaria-foundation).
causeNo
questionNoThe donor's question in their own words.
budget_usdNoGift size in US dollars; adds the modeled say_as sentences for one named charity.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already mark this read-only and idempotent, and the description adds substantial behavioral context: it fails closed, computes no new figures, never ranks across causes, discloses modeled figures, and explains edge-case handling. This is far more than restating the annotations.

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

Conciseness2/5

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

The first sentence is well front-loaded, but the body is a sprawling changelog of 'since wave N' implementation notes rather than a concise definition. Much of the detail repeats internal version history and would be better placed elsewhere.

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 tool with no output schema, the description is very complete: it itemizes returned fields, failure behavior, refusal rules, and specialized answer modes. An agent has enough information to call it and interpret the response.

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?

The schema already covers org, question and budget_usd well, but the description adds useful meaning: org accepts an id or slug, budget_usd only adds estimate_impact-style sentences for one named charity, and dollar amounts in the question are read as budget when budget_usd is absent. Cause is less explicitly explained, which keeps this from a 5.

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 opening sentence states a specific purpose — call first for any donor question — and the return fields are enumerated, so an agent can tell this is a router/answer tool rather than a search or estimate tool. It also distinguishes itself explicitly from siblings such as search_orgs and estimate_impact.

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?

Guidance is explicit: 'Call this first for any donor question', with named conditions for many question types and clear alternatives like estimate_impact. It states when specialized branches apply and what to do instead on failure, so little is left to inference.

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