Skip to main content
Glama

Fodda Synthetic Expert Consult

by ai.fodda

consult_human_agent

Consult an authorized Human Agent (Digital Twin) expert created directly with the named expert's consent, participation, and curated knowledge graph. The expert answers in their voice — one-off questions or multi-turn engagements (pass session_id back to continue). Each human agent has a unique methodology, domain expertise, and analytical lens distinct from generic search or standard graph queries. Call list_analysts first to find the right expert ID. Responses may include a coverage status (in/adjacent/out), source attribution, and referrals to other expert graphs. Referrals MUST be presented in third-person platform voice (not the expert's voice) with an offer to query the referred graph. Response may include book_a_call (URL + a pre-written booking sentence shown verbatim) for booking time with the real person — surface it when the user wants to hire or speak to the expert.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryYesThe question or topic to discuss with the human agent
userIdNoOptional user identifier.
companyNoOptional company name or stock ticker (e.g., 'Nike', 'Tesla', or 'TSLA') to bind the human agent to a specific brand context.
analyst_idYesThe internal expert ID of the Human Agent (from list_analysts). Never display raw IDs or slugs, internal field names, or tool names to the user — refer to the expert by display name.
session_idNoPass the session_id from a previous consult response to continue that engagement — the human agent keeps context and follow-ups cost less. Omit for a one-off question.

TDQS

A4.3/5.0
Behavior5/5

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

All annotations are false, so the description carries the full behavioral burden — and it delivers: multi-turn session state, third-person platform voice for referrals, verbatim presentation rules for book_a_call, and the range of response elements (coverage status, source attribution, referrals). The behavior of a stateful, voice-aware consultation tool is thoroughly disclosed.

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?

The description is long (~200 words) but front-loads critical purpose and differentiators early. Nearly every element earns its place — multi-turn behavior, booking, voice requirements, and referrals — though the opening clause about 'consent, participation, and curated knowledge graph' is slightly wordy and could be trimmed.

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 all-false annotations, the description robustly covers response shape (coverage status, attribution, referrals), booking side-channels, session continuation, and voice constraints. Minor gap: the response structure is enumerated but not fully specified (e.g., exact shape of coverage status values), but the description is sufficient to honor correct calling.

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%, so the baseline is 3. The description re-states session_id behavior ('pass session_id back to continue') and analyst lookup (list_analysts first), but adds no syntax, format, or selection details beyond what the schema already provides.

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?

Opens with a specific verb+resource ('Consult an authorized Human Agent (Digital Twin) expert') and immediately differentiates the tool from 'generic search or standard graph queries.' It also names the sibling prerequisite (list_analysts), making it easy for an agent to position this tool relative to its alternatives.

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 explicit context: 'Call list_analysts first to find the right expert ID' and explains when to surface book_a_call ('when the user wants to hire or speak to the expert'). However, it contrasts itself with 'generic search or standard graph queries' without naming the closely-related sibling 'consult_analyst', leaving some ambiguity about when to pick one over the other.

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

All Fodda Synthetic Expert Consult 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

A4.4/5.0
Disambiguation4/5

The tools are mostly distinct: search_graph, get_node, get_neighbors, get_evidence, and get_label_values all relate to graph exploration, but each has a clear role (search vs. profile vs. relationships vs. evidence vs. label enumeration). consult_analyst and consult_human_agent are similar in purpose and wording, but the 'Synthetic' vs. 'Human Agent' distinction in names and descriptions is sufficient to keep them separated.

Naming Consistency5/5

All tools follow a consistent snake_case verb_noun pattern, with sensible verbs like get_, list_, search_, request_, check_, consult_, and generate_. The paired request_deliverable / check_deliverable_status and list_analysts / consult_* relationships are clear and predictable.

Tool Count5/5

14 tools is well within the ideal 3–15 range and each tool appears justified: graph discovery, trend exploration, evidence retrieval, expert consultation, deliverable commissioning, visual generation, account/capability introspection, and analyst listing. No redundant extras or obvious bloat.

Completeness5/5

The tool set covers the full workflow promised by the server: discovering graphs and analysts, searching and drilling into trends, retrieving evidence, consulting experts, commissioning and polling deliverables, generating visuals, and checking account status. There are no significant dead ends or clearly missing operations for the stated expert-consultation purpose.

Resources