Professional-grade MCP gateway for high-fidelity strategic intelligence. Provides autonomous agents with gated access to sovereign audits, frontier science retrospectives, and macroeconomic synthesis.
Scored across 11 tools
Most tools have distinct retrieval or verification purposes, but there is overlap between ask_intelligence_rag and search_intelligence_matrix, and between get_alpha_gap and get_model_record. Descriptions help, but an agent could still hesitate between semantic Q&A, vector search, and keyword dossier search.
All tool names use consistent snake_case with a clear verb_noun structure: ask_intelligence_rag, get_alpha_gap, get_dossier_delta, list_dossiers, search_dossiers, verify_commitment, etc. No mixed conventions or vague verbs.
11 tools is a reasonable size for an intelligence retrieval platform, covering multiple access modes and verification. However, optimize_codon is an unrelated biocomputing outlier that slightly dilutes the otherwise well-scoped set.
The server covers many read-oriented intelligence operations: listing, searching, reading, asking RAG questions, querying the graph, checking alpha gaps, model records, deltas, and verifying commitments. It lacks write/update operations and a direct alpha-gap listing, but the core consumption surface is largely complete.
Ask a natural-language question and receive structured intelligence context retrieved from Tresslers Group dossiers via RAG (Retrieval Augmented Generation). Returns relevant document chunks, source citations, conviction metadata, and graph neighborhood data. The calling LLM should synthesize the returned context into a coherent answer.
| Name | Required | Description | Default |
|---|---|---|---|
| question | Yes | Natural language question (e.g., 'What are the key geopolitical risks in sovereign AI policy?'). | |
| max_sources | No | Maximum number of source dossier chunks to retrieve (default 5, max 8). |
| Name | Required | Description |
|---|---|---|
| content | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses that the tool performs retrieval (RAG) and returns multiple data types, confirming it is a read-only operation. It does not mention side effects, rate limits, or auth needs, but given the nature of a query tool, the description is sufficiently transparent beyond what schema/annotations provide.
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 concise sentences. The first sentence states the primary action and resource, the second lists return types, and the third provides usage guidance. No redundant or unnecessary information, and key points are front-loaded.
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 (RAG with multiple return types) and the presence of an output schema, the description adequately explains what the tool returns. It covers the retrieval method and expected outputs but could be more complete by mentioning potential limitations or error scenarios. Still, it provides sufficient context for an agent to use the tool effectively.
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?
Both parameters have schema descriptions (100% coverage) and are clear. The tool description adds no additional semantic value beyond the schema (e.g., no extra formatting or usage hints). Baseline score of 3 is appropriate since schema already documents parameters adequately.
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 purpose: asking a natural-language question and receiving structured intelligence context from Tresslers Group dossiers via RAG. It lists specific return types (document chunks, source citations, etc.) and distinguishes from siblings which are more specialized (e.g., query_knowledge_graph for graph queries, read_dossier for single dossiers).
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 for natural-language questions across dossiers and advises the LLM to synthesize returned context into an answer. However, it does not explicitly state when to use this tool versus its siblings (e.g., list_dossiers, read_dossier) or provide exclusion criteria, leaving the agent to infer appropriate contexts.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Retrieves prediction market Alpha Gaps comparing Tresslers Group Bayesian model odds against Polymarket order books, along with Brier scores, calibration alpha (+3,480 bps benchmark), and cryptographic SHA-256 pre-commitments.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of Alpha Gap records to return. | |
| status | No | Filter by status or settlement type (e.g., 'CONTRACT_SETTLED', 'OUTCOME_TRACKED', 'RESOLVED', 'PENDING', 'ALL'). | |
| category | No | Optional filter by strategic intelligence domain. | |
| min_divergence | No | Minimum absolute divergence gap in percentage points (e.g. 20 for >= 20% gap). | |
| settlement_type | No | Filter by settlement tier: 'contract_settled', 'outcome_tracked', 'unscored_archive', or 'all'. |
| Name | Required | Description |
|---|---|---|
| content | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. 'Retrieves' implies a read-only operation and it usefully discloses what payload comes back (Brier scores, calibration alpha benchmark, SHA-256 pre-commitments), but it says nothing about permissions, rate limits, pagination, or defaults for the optional filters.
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?
A single front-loaded sentence that delivers the operation and payload without filler. It is dense with domain jargon ('Brier scores', 'calibration alpha') but every clause conveys substantive information.
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?
An output schema exists, so return-format explanation is unnecessary, and the five optional filters are fully documented in the schema. The main gap is the absence of usage guidance and behavioral constraints, which leaves the definition slightly thin for a tool with no annotations.
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 100%, so all five parameters are already documented in the schema with enum values and examples. The description adds no parameter-level syntax or semantics beyond what the schema provides, so the baseline 3 applies.
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?
States a specific verb ('Retrieves') and a well-defined resource (prediction market Alpha Gaps), plus the data sources being compared (Bayesian model odds vs Polymarket order books) and the accompanying metrics. It is highly distinctive, though it never explicitly positions itself against siblings like get_dossier_delta or search_intelligence_matrix.
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?
There is no statement of when to use this tool versus alternatives, no prerequisites, and no exclusions. The agent can only infer usage from the filter parameters in the schema, which is not guidance from the description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Queries intelligence updates and conviction deltas attested since a specific UTC timestamp.
| Name | Required | Description | Default |
|---|---|---|---|
| since_timestamp | Yes | ISO UTC timestamp (e.g., '2026-05-01T00:00:00Z'). |
| Name | Required | Description |
|---|---|---|
| content | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, description carries full burden. It uses 'queries' indicating a read-only operation, and specifies input format. Lacks details on authentication or error handling, but adequately communicates safe behavior for a read tool.
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?
Single sentence with 10 words, perfectly front-loaded with the key verb 'Queries'. No wasted words; every part contributes to understanding.
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 output schema exists and only one parameter, description is adequate. It specifies the condition clearly. Lacks mention of pagination or limits, but sufficient for a straightforward delta query.
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 100% with the parameter 'since_timestamp' already described as an ISO UTC timestamp. The description reinforces the condition ('since a specific UTC timestamp') but adds no new detail beyond the schema. Baseline 3 is appropriate.
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?
Description clearly states the verb 'queries' and the resource 'intelligence updates and conviction deltas' with a specific condition 'since a specific UTC timestamp'. It distinguishes from sibling tools like 'list_dossiers' or 'ask_intelligence_rag' which likely serve different purposes.
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?
Description implies usage when needing updates since a timestamp, but does not explicitly state when not to use it or mention alternative tools. Provides no exclusions or context for avoiding misuse.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Queries the public calibration and backtest ledger of Tresslers Group sovereign intelligence models. Supports filtering by settlement type ('contract_settled' for live prediction markets, 'outcome_tracked' for internal foresight models, 'unscored_archive' for pre-commitment history, or 'all'). Returns Brier calibration scores, transparent failure analysis, and verifiable primary source URLs.
| Name | Required | Description | Default |
|---|---|---|---|
| status | No | Filter by resolution status (default: 'ALL'). | |
| category | No | Optional filter by intelligence pillar/category. | |
| settlement_type | No | Filter by settlement tier: 'contract_settled' (live prediction market order-books), 'outcome_tracked' (internal Bayesian foresight), 'unscored_archive' (pre-commitment era), or 'all' (default). |
| Name | Required | Description |
|---|---|---|
| content | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations are empty, so the description carries the full burden — and it largely delivers: 'public' signals no privileged access needed, 'Queries' signals a read operation, and the return contents (Brier scores, failure analysis, source URLs) are disclosed. It stops short of explicitly stating non-destructiveness, empty-result behavior, or pagination/limits, but the query-only profile is clearly conveyed and nothing contradicts the empty annotations.
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?
Three sentences, purpose first, with zero filler: what it queries, which filters exist and what the values mean, and what it returns. The dense settlement_type mapping earns its sentence because it replaces a whole domain-to-enum lookup the agent would otherwise have to guess.
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 a fully documented input schema and an existing output schema, the description covers the essentials: resource identity, filter semantics, and the nature of returned data. What is missing is guidance on how status and settlement_type interact and any mention of result limits, plus the two enums use inconsistent casing (ALL/RESOLVED/PENDING vs. all/contract_settled/...) — minor but real wrinkles for correct invocation.
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 coverage is 100%, so the baseline is 3, but the description adds real meaning beyond the schema by translating each settlement_type enum value into a domain concept (live prediction markets, internal foresight models, pre-commitment history, all). This lets an agent map natural-language intent to the correct enum value; status and category are adequately documented by the schema itself.
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?
Opens with a specific verb and resource: 'Queries the public calibration and backtest ledger of Tresslers Group sovereign intelligence models.' The ledger focus and read verb clearly separate it from the dossier, knowledge-graph, RAG, and matrix siblings without needing to name them, since no sibling covers model calibration/backtest records.
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?
Provides explicit context for when to use it: whenever calibration, backtest, or Brier-score data for Tresslers Group models is needed. The settlement_type mapping ('contract_settled' for live prediction markets, 'outcome_tracked' for internal foresight, 'unscored_archive' for pre-commitment history) tells the agent which filter matches which user intent, though there are no when-not or alternative-routing statements naming siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Returns a list of all available intelligence dossier slugs.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
| Name | Required | Description |
|---|---|---|
| content | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description simply declares a read operation. It adds no details about access controls, ordering, or pagination, but the straightforward nature limits the need.
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?
Single sentence, front-loaded, zero waste. Every word serves a purpose.
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?
Adequate for a simple listing tool, but could mention that results depend on user permissions or that it only returns slugs. Having an output schema reduces the need, but slightly more context would help.
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?
There are no parameters, so the baseline of 4 applies. The description adds no further param info, but none is needed.
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 it returns a list of all available intelligence dossier slugs, using specific verb and resource. However, it does not explicitly differentiate from sibling tools, which is adequate but not top-tier.
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?
No guidance on when to use this tool versus alternatives like read_dossier or search_intelligence_matrix. The agent receives no context for selection.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Optimizes a protein (amino acid) or cDNA coding sequence for maximal recombinant expression yield in a target host organism using the Logos biocomputing engine. Executes Codon Adaptation Index (CAI) maximization, GC-content harmonization, restriction site avoidance, and ribosomal consensus leader generation. Research Use Only (RUO). In-silico modeling only; select-agent and regulated pathogen sequence optimization is strictly prohibited under 42 CFR 73 and BWC compliance. Free and open to all AI agents.
| Name | Required | Description | Default |
|---|---|---|---|
| host | No | Target expression organism: 'e_coli', 'h_sapiens' (HEK293), 'c_griseus' (CHO), 's_cerevisiae', 'p_pastoris', 'v_natriegens', 'n_benthamiana', 'a_thaliana'. Default: 'e_coli' | |
| sequence | Yes | Amino acid sequence (single-letter uppercase e.g. 'MSKGEELFT...') or DNA coding sequence to optimize. | |
| gc_target | No | Target global GC percentage (e.g., 52 for E. coli, 58 for Human). Optional. |
| Name | Required | Description |
|---|---|---|
| content | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations are empty, so the description carries the responsibility. It discloses in-silico-only behavior, RUO status, usage restrictions, and the fact that it is freely open to agents. It does not explicitly state side effects or that no data persists, but the in-silico modeling statement covers the main safety profile.
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?
Purpose is in the first sentence, followed by concrete method details, then compliance. No filler or repetition; every sentence carries distinct information.
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 gives purpose, algorithm behaviors, host context, compliance constraints, and access policy. It does not state the output/return format or default host, but the schema already covers host options. Slightly lacking an explicit success/response description, otherwise 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?
Input schema already documents all three parameters with clear descriptions (including host enum). The description adds useful context—protein vs cDNA input and GC-content harmonization—but does not clarify defaults or format details beyond the schema. This meets the baseline without extending it.
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?
Names a specific operation (optimize), the exact input types (protein amino acid or cDNA coding sequence), the goal (maximal recombinant expression yield), and the target host context. The method list (CAI, GC harmonization, restriction-site avoidance, leader generation) leaves no ambiguity about what the tool does.
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?
Clear use context: optimizing coding sequences for expression in a listed host. States explicit prohibitions (select-agent/regulated sequences) and the RUO/in-silico constraint. No alternatives or sibling comparisons are given, so it does not fully meet the 'when to use vs alternatives' bar.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Traverses the multi-hop conceptual knowledge graph across entities (GraphRAG). Free preview available for direct 1-hop adjacencies. Deeper reasoning (2-3 hops) requires x402 settlement.
| Name | Required | Description | Default |
|---|---|---|---|
| depth | No | Graph traversal hop depth (1 for free preview, 2 to 3 for deep reasoning). | |
| entity_id | Yes | Target conceptual entity or dossier slug (e.g., 'Quantum AI', 'ThinkForge'). | |
| payment_proof | No | Standard x402 signed USDC transaction proof (0x...). Required for multi-hop graph access. |
| Name | Required | Description |
|---|---|---|
| content | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With empty annotations, the description must fully convey behavior. It discloses that deeper hops require payment and that a free preview exists, but does not cover other aspects like rate limits, permissions, or potential errors. The behavioral context is adequate but not thorough.
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?
Two sentences with no redundant words. First sentence states purpose, second explains monetization structure. Perfectly front-loaded and concise.
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 an output schema exists (not detailed here), the description covers core functionality and pricing. It is complete enough for an agent to decide usage, though it omits potential error states (e.g., invalid payment_proof). Still, it's well-rounded.
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 coverage is 100%, so baseline is 3. The description adds meaningful context: 'depth' of 1 is free, 2-3 requires payment_proof with x402 signature. This enriches the schema descriptions, justifying a higher score.
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 traverses a multi-hop knowledge graph (GraphRAG) with specific verb 'traverses' and resource 'knowledge graph'. It distinguishes from siblings like ask_intelligence_rag (which likely answers questions) by emphasizing multi-hop traversal.
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 explicitly defines when to use the free preview (1-hop) vs paid (2-3 hops) via x402 settlement. However, it does not mention alternatives among siblings, such as when to use ask_intelligence_rag instead for single-hop queries.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Reads the pure text contents of a specific intelligence dossier. Requires x402 payment proof for premium intelligence. Without payment proof, returns a high-fidelity strategic excerpt and payment challenge.
| Name | Required | Description | Default |
|---|---|---|---|
| slug | Yes | The slug of the dossier to read (e.g., 'sovereign-ai-state-national-policy-2026'). | |
| payment_proof | No | Standard x402 signed USDC transaction proof (0x...). Required for full decrypted access. |
| Name | Required | Description |
|---|---|---|
| content | No | |
| isError | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, description carries full burden. Discloses that payment proof grants full access; without it, returns a strategic excerpt and challenge. This is good transparency for a read-only tool, though no mention of side effects, rate limits, or auth details beyond payment.
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?
Two concise sentences front-loading the main purpose and then critical usage condition. No fluff; every sentence adds value.
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?
Covers core behavior including payment proof implications. Output schema likely details return format, so not needed here. Missing any mention of how to handle errors or limits, but overall sufficient for a focused read tool.
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 coverage is 100%, so baseline is 3. The description adds context about payment proof behavior but does not elaborate on parameter syntax or constraints beyond what schema already provides. No additional value for slug parameter.
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?
Clearly states it reads pure text contents of a specific dossier. However, does not differentiate from siblings like get_dossier_delta or ask_intelligence_rag, which could cause confusion about which tool to use for similar tasks.
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?
Explicitly describes when payment proof is required and what happens without it. Provides context for choosing this tool for full text or partial excerpt. Could be improved by mentioning when not to use it (e.g., for filtered or delta queries).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Searches and filters across all published Tresslers Group intelligence dossiers by keywords, strategic domain/category, tags, or conviction threshold.
| Name | Required | Description | Default |
|---|---|---|---|
| tag | No | Optional tag filter (e.g., 'sovereign-ai', 'energy-transition'). | |
| limit | No | Maximum number of dossiers to return (default: 5, max: 20). | |
| query | Yes | Search query or keywords to match across title, excerpt, content, and tags. | |
| category | No | Optional category filter (e.g., 'Geopolitics & Sovereign Policy', 'Energy & Infrastructure'). | |
| min_conviction | No | Minimum conviction threshold (0.0 to 1.0, e.g., 0.85). |
| Name | Required | Description |
|---|---|---|
| content | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations are empty, so the description carries the full behavioral burden. It does disclose one useful scoping fact — only 'published' dossiers are covered — but says nothing about ranking, permissions, rate limits, pagination beyond the schema's limit field, or what happens when no results match.
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?
A single front-loaded sentence with no filler, stating the action and scope immediately. It is efficient, though it is perhaps too compact given the tool's five parameters and lack of sibling differentiation.
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?
An output schema exists, so return values need no explanation, and all five parameters are fully documented in the schema. However, with no annotations and eleven sibling tools including overlapping list/read/search tools, the description is thin on the operational context an agent needs to choose and use it confidently.
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 100%, so every parameter (tag, limit, query, category, min_conviction) is already documented in the schema, including examples and defaults. The description only restates those facets and adds no new syntax, format, or constraint detail, so the baseline of 3 applies.
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 gives a specific verb ('searches and filters') and resource ('published Tresslers Group intelligence dossiers') and enumerates the four filter dimensions an agent can use. It does not, however, distinguish this tool from close siblings like list_dossiers or search_intelligence_matrix, so the agent must still infer the boundary.
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?
There is no when-to-use, when-not-to-use, or alternative-tool guidance. The word 'search' and the listed facets imply it is the keyword/faceted lookup path, but with siblings such as list_dossiers and search_intelligence_matrix present, the description leaves the routing decision entirely to inference.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Executes a semantic vector similarity search across the entire ThinkForge intelligence substrate. Returns relevant snippets and strategic conviction metadata.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max results to return (default 5, max 10). | |
| query | Yes | Semantic research question (e.g., 'What are the geopolitical vulnerabilities in green hydrogen supply chains?'). | |
| filter | No | Optional SQL-like metadata filter (e.g., 'convictionScore >= 0.85'). |
| Name | Required | Description |
|---|---|---|
| content | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations empty, so description must cover behavior. Only gives high-level purpose and outputs; no detail on side effects (none), error handling, or filtering behavior beyond schema. Could mention that it is read-only.
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?
Single sentence that effectively communicates the core action and result. Efficient and front-loaded.
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 has 3 parameters fully described and output schema, the description is adequate but could better contextualize when to use this tool over siblings, and the meaning of 'conviction metadata'.
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 already provides full descriptions for all parameters (100% coverage). Description rephrases but adds no new semantic meaning beyond what's in 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?
Clearly states it executes a semantic vector search across the entire intelligence substrate and returns relevant snippets with conviction metadata. Differentiates from siblings like ask_intelligence_rag which is more QA-focused.
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?
No explicit when-to-use or when-not-to-use compared to siblings. Implicitly for broad semantic search, but lacks guidance compared to alternatives like ask_intelligence_rag.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Cryptographically verifies a predictive alpha pre-commitment against the immutable SHA-256 ledger using either a 64-character hash digest or canonical preimage parameters.
| Name | Required | Description | Default |
|---|---|---|---|
| hash | No | 64-character lowercase hexadecimal SHA-256 commitment digest. | |
| preimage | No | Full pipe-delimited UTF-8 canonical preimage string (YYYY-MM-DD|question|model_odds|target_dossier_slug). | |
| model_odds | No | Model odds integer component (0-100). | |
| dossier_slug | No | Target dossier slug component. | |
| dispatch_date | No | Dispatch date component (YYYY-MM-DD). | |
| market_question | No | Exact market question component. | |
| canonical_preimage | No | Alternative key for canonical preimage string. |
| Name | Required | Description |
|---|---|---|
| content | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden. It usefully discloses that verification is cryptographic and checked against an immutable ledger, but says nothing about what a failed/mismatched verification means, whether the call is read-only, or any auth/rate constraints. An output schema exists, so return-value details are legitimately omitted.
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?
A single sentence that front-loads the action and the object of verification, with zero filler. Every clause (hash vs. preimage, immutable ledger) carries information.
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 zero-required-parameter, 100%-documented tool with an output schema, the description covers the what and the how-to-invoke. It could be stronger by noting that at least one of the two input modes must be supplied, since no parameter is required.
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 coverage is 100%, so the baseline is 3, but the description goes further by explaining that the 7 parameters form two mutually exclusive input modes (a 64-character hash OR the canonical preimage components). That either/or structure is not evident from the flat schema alone.
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 a specific verb (cryptographically verifies) plus the exact resource (a predictive alpha pre-commitment against the immutable SHA-256 ledger). No sibling tool in the list performs verification, so this is unambiguously distinguishable from the read/search/dossier tools around it.
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?
It clarifies the two invocation paths (hash digest vs. canonical preimage parameters), which is implied usage guidance for calling it. However, it never states when this tool should be chosen over alternatives, nor any prerequisites such as the commitment needing to have been registered first.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
get_alpha_gapsearch_dossiersverify_commitmentget_model_record1 field changedInput schema / properties / settlement_typeAdded value: +{
+ "description": "Filter by settlement tier: 'contract_settled' (live prediction market order-books), 'outcome_tracked' (internal Bayesian foresight), 'unscored_archive' (pre-commitment era), or 'all' (default).",
+ "enum": [
+ "all",
+ "contract_settled",
+ "outcome_tracked",
+ "unscored_archive"
+ ],
+ "type": "string"
+}get_model_recordoptimize_codonask_intelligence_ragget_dossier_deltalist_dossiersquery_knowledge_graphread_dossiersearch_intelligence_matrix
Add one secure layer between your agents and this server.