Stress-test a decision through named thinkers' lenses: assumptions, counter-arguments, receipt.
Glama MCP Gateway
Connect through Glama MCP Gateway for full control over tool access and complete visibility into every call.
Full call logging
Every tool call is logged with complete inputs and outputs, so you can debug issues and audit what your agents are doing.
Tool access control
Enable or disable individual tools per connector, so you decide what your agents can and cannot do.
Managed credentials
Glama handles OAuth flows, token storage, and automatic rotation, so credentials never expire on your clients.
Usage analytics
See which tools your agents call, how often, and when, so you can understand usage patterns and catch anomalies.
Average 4.3/5 across 5 of 5 tools scored.
Each tool has a clearly distinct role: listing lenses, comparing two lenses, stress-testing a decision, extracting assumptions, and generating receipts. The detailed descriptions clarify boundaries, and even overlapping features like assumption extraction in both assumption_map and stress_test_decision serve different contexts.
All tool names use snake_case and are readable, but the verb_noun pattern is not uniform: list_lenses and compare_lenses follow it, while assumption_map and council_receipt are noun_noun. This minor deviation prevents a perfect score but does not cause confusion.
With exactly 5 tools, the server is well-scoped for its purpose. Each tool earns its place and covers a distinct step in the consultation workflow without redundant or unnecessary additions.
The set covers the core workflow: discovering lenses, comparing them, stress-testing decisions, extracting assumptions, and creating shareable receipts. However, stress_test_decision does not allow manually selecting which lenses to consult, which is a notable gap for users wanting to test against specific thinkers beyond the two-lens compare tool.
assumption_mapAInspectUdtræk centrale antagelser bag en beslutning/plan, hver mærket: evidens-understøttet / uprøvet / ikke-falsificerbar.
PUBLIC_DEMO-mode: rate-limitet (default 5/min + 30/time, eget bucket). Over grænsen
returneres {error:"rate_limited", retry_after_s, scope_note}. Svaret får et
scope_note-felt med demo-disclosuren.
| Name | Required | Description | Default |
|---|---|---|---|
| decision | Yes |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It transparently discloses rate limits (default 5/min + 30/hour), the error format for exceeding limits, and the addition of a 'scope_note' field. This goes beyond basic functional description, though it does not mention side effects or authentication requirements.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and front-loaded, starting with the primary purpose in the first sentence. The second paragraph provides operational details (rate limits, error format) that are each useful. Every sentence earns its place, with no filler or repetition.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with a single parameter and an output schema, the description is reasonably complete. It covers the tool's core function, parameter meaning, rate limiting, and error behavior. The existence of an output schema reduces the need to explain return values in detail, and the description adequately covers other essential aspects.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has one required parameter 'decision' with no description (0% schema coverage). The description compensates by clarifying that the parameter represents the decision/plan from which assumptions are extracted. This adds meaningful semantics beyond the bare schema, though it does not provide format examples or types beyond the string type.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's function with a specific verb ('Udtræk' / extract) and resource ('centrale antagelser bag en beslutning/plan' / central assumptions behind a decision/plan). It also specifies the output categories (evidence-supported, untested, non-falsifiable), making it distinct from siblings like compare_lenses or stress_test_decision.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus its siblings. It lacks any mention of use cases, alternatives, or exclusions. The only context is a mention of PUBLIC_DEMO-mode rate limiting, which is operational, not usage guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
compare_lensesAInspectTo navngivne tænkere (se list_lenses) på samme problem, side om side med korpus-grundlag. Afgør IKKE enighed/konflikt for dig — det er din vurdering (never-write-for-you).
PUBLIC_DEMO-mode: rate-limitet (default 5/min + 30/time, eget bucket). Over grænsen
returneres {error:"rate_limited", retry_after_s, scope_note}. Svaret får et
scope_note-felt med demo-disclosuren (nyt felt — disclaimer uændret).
| Name | Required | Description | Default |
|---|---|---|---|
| lens_a | Yes | ||
| lens_b | Yes | ||
| problem | Yes |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Since no annotations are provided, the description carries the full burden. It discloses rate limits (5/min + 30/hour), the exact error response format, and the addition of a `scope_note` field. This is substantive behavioral detail, though it omits the successful return structure (which may be covered by the output schema).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise and front-loaded with purpose. Every sentence adds unique value: purpose, non-interference instruction, rate limit, error format, and field changes. No redundant or filler content.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With an output schema present and only three simple parameters, the description adequately covers what the tool does, when to use it, its limitations, and rate-limiting behavior. It could add more detail on the successful output or prerequisites, but it is largely complete for the tool's complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description must compensate. It explains that lens_a and lens_b are named thinkers from list_lenses and that problem is the shared problem, but it does not define each parameter explicitly or provide examples. This is partial but not complete compensation for the absent parameter descriptions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description states the tool compares two named lenses on a shared problem side-by-side with corpus grounding, which is a specific verb+resource+scope. It also distinguishes itself by explicitly saying it does NOT decide agreement/conflict for you, and references list_lenses for valid lens names.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives a clear usage context: compare two named lenses (from list_lenses) on a problem, with the caveat that it will not make the judgment for you. It does not explicitly name alternative tools, but the 'never-write-for-you' rule and reference to list_lenses provide practical usage guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
council_receiptAInspectKompakt, delbart kvitteringskort fra et stress_test_decision-resultat: top-3 stærkeste
modargumenter + billigste falsifikationstest. sign er OPT-IN (aldrig default/ledende) og
NÆGTES hvis en kilde-linse i resultatet er trunkeret (ufuldstændigt svar signeres aldrig).
Formatering uændret i BEGGE modes (ren formatering, ingen ny backend-inferens, ingen
rate-limit). sign=True er derimod HARD-REFUSED i PUBLIC_DEMO uanset om
COUNCIL_RECEIPT_SIGNING_KEY er sat i processen (red-team-fund 2026-08-04, robusthed-runde
§3): uden denne guard er council_receipt en anonym signerings-orakel — result er
fuldt kalder-leveret, og enhver anonym bruger der leverer et ikke-trunkeret
lenses-array ville få Humanifieds Ed25519-nøgle til at signere en vilkårlig
kalder-forfattet "council receipt" som en ægte attestation. Lukningen er kodelag-nu,
IKKE afhængig af om nøglen ved et uheld ligger i demo-processens env.
| Name | Required | Description | Default |
|---|---|---|---|
| sign | No | ||
| result | Yes |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full responsibility. It thoroughly discloses behavior: pure formatting, no backend inference, no rate-limit, sign refusal conditions, and the security rationale for hard-refusing in PUBLIC_DEMO. This is extensive and valuable context.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description front-loads the core purpose and then dives into detailed security explanations, including a red-team finding with date and section reference. This is dense and verbose, but the information is relevant. It could be better structured, but it is not wasteful.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description covers purpose, input source, output contents, security behaviors, mode differences, and rate-limit absence. An output schema exists, so return values need not be explained. For a tool with this complexity, the description is remarkably complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, so the description compensates well. It explains that `sign` is OPT-IN and denied under truncation, and that `result` is fully caller-supplied and contains a `lenses` array. While not exhaustive, it adds significant meaning beyond the bare schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly indicates the tool creates a compact, shareable receipt card from a stress_test_decision result, with specific output contents (top-3 counterarguments and cheapest falsification test). It distinguishes itself from siblings by referencing its source tool, though it does not explicitly contrast with other tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage after stress_test_decision and provides detailed conditions for the sign parameter (OPT-IN, denied if truncated, hard-refused in PUBLIC_DEMO). However, it does not explicitly state when to use this tool over alternatives like compare_lenses or assumption_map.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
list_lensesAInspectRosteret af faktisk konsulterbare tænker-linser + ærlig groundedness-status (dyb / tynd / kort-tynd korpus-dybde). Viser KUN linser der er nåelige via /council/consult — aldrig den fulde rå roster. Uændret i BEGGE modes — ingen ny backend-inferens, ingen rate-limit, ingen demo-wrap.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| result | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden and does so well. It discloses that results are unchanged in both modes, and explicitly states there is no backend inference, no rate limiting, and no demo wrapping—honest and useful non-functional information.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is three sentences, each adding distinct value: what is returned, the strict scope limitation, and behavioral guarantees. It is front-loaded with the core purpose and avoids filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given zero parameters, an output schema, and sibling context, the description covers the essential facts: reachability via /council/consult, groundedness status values, and invariants across modes. It is sufficiently complete for an agent to select and call this tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has zero parameters, so the baseline is 4. The description appropriately focuses on output semantics and doesn't need to explain parameters that don't exist.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The Danish description clearly states the action ('Viser' / shows) and the specific resource: the roster of actually consultable thinker lenses with groundedness status. It distinguishes itself from siblings by explicitly noting it shows ONLY lenses reachable via /council/consult and never the full raw roster.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives clear context: use this tool to list only consultable lenses, not the full roster. It does not name alternative sibling tools like compare_lenses, but the boundary of what this tool returns versus the full roster is unambiguous.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
stress_test_decisionAInspectStress-test et forslag/beslutning. Auto-vælger n_lenses relevante, korpus-grundede tænker-linser (/council/rank, filtreret mod konsulterbar allowlist) og konsulterer dem SAMTIDIGT. Returnerer pr. linse: skjulte antagelser, stærkeste modargument, falsificerbare tests, ukendte forhold, og hvad ville ændre vurderingen — samt ærlig groundedness- og trunkerings-status. ADVISORY: informerer, beslutter ALDRIG for dig.
PUBLIC_DEMO-mode: n_lenses hard-cappes til min(n, 3) (fan-out-bind). Rate-limitet
(default 5/min + 30/time, eget bucket for dette tool). Over grænsen returneres
{error:"rate_limited", retry_after_s, scope_note}. Svaret får et scope_note-felt med
demo-disclosuren (nyt felt — disclaimer uændret).
| Name | Required | Description | Default |
|---|---|---|---|
| n_lenses | No | ||
| proposal | Yes |
| Name | Required | Description |
|---|---|---|
No output parameters | ||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries full burden, and it excels: it discloses auto-selection of lenses, simultaneous consultation, per-lens return contents, honest groundedness/truncation status, advisory-only nature, PUBLIC_DEMO caps on n_lenses, rate limits, and the exact error response shape. This goes far beyond typical descriptions.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is dense but every sentence earns its place: main action, per-lens outputs, advisory scope, and demo-specific constraints (cap, rate limits, error shape, scope_note). It is front-loaded with the core purpose and structured so the most important behavioral details appear first, with operational details following.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's complexity and the existence of an output schema, the description covers purpose, parameter behavior, return structure, safety constraints, rate limits, and demo-mode deviations. It even explains that 'scope_note' is a new field while 'disclaimer' remains unchanged, leaving little ambiguity for the agent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 0%, but the description compensates by explaining n_lenses as the number of relevant lenses auto-selected and capping it in demo mode. It also identifies the proposal as the subject being stress-tested. It does not provide full parameter-level formalities, but it adds meaning beyond the raw schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description begins with a specific verb and resource: 'Stress-test et forslag/beslutning' (stress-test a proposal/decision). It clearly distinguishes the tool from siblings like 'assumption_map' and 'compare_lenses' by describing its unique output per lens (hidden assumptions, strongest counterargument, falsifiable tests, unknowns, and what would change the assessment).
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description clearly states the tool is advisory ('ADVISORY: informerer, beslutter ALDRIG for dig') and describes when it is used (to stress-test a proposal). However, it does not explicitly name alternatives or state when NOT to use this tool versus siblings, so it stops short of full comparative guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Claim this connector by publishing a /.well-known/glama.json file on your server's domain with the following structure:
{
"$schema": "https://glama.ai/mcp/schemas/connector.json",
"maintainers": [{ "email": "your-email@example.com" }]
}The email address must match the email associated with your Glama account. Once published, Glama will automatically detect and verify the file within a few minutes.
Control your server's listing on Glama, including description and metadata
Access analytics and receive server usage reports
Get monitoring and health status updates for your server
Feature your server to boost visibility and reach more users
For users:
Full audit trail – every tool call is logged with inputs and outputs for compliance and debugging
Granular tool control – enable or disable individual tools per connector to limit what your AI agents can do
Centralized credential management – store and rotate API keys and OAuth tokens in one place
Change alerts – get notified when a connector changes its schema, adds or removes tools, or updates tool definitions, so nothing breaks silently
For server owners:
Proven adoption – public usage metrics on your listing show real-world traction and build trust with prospective users
Tool-level analytics – see which tools are being used most, helping you prioritize development and documentation
Direct user feedback – users can report issues and suggest improvements through the listing, giving you a channel you would not have otherwise
The connector status is unhealthy when Glama is unable to successfully connect to the server. This can happen for several reasons:
The server is experiencing an outage
The URL of the server is wrong
Credentials required to access the server are missing or invalid
If you are the owner of this MCP connector and would like to make modifications to the listing, including providing test credentials for accessing the server, please contact support@glama.ai.
No comments yet. Be the first to start the discussion!