connect_startBegin authentication. Send the user's work email; Victano mails them a six-digit code valid for 15 minutes and returns a request_id. Ask the user for the code, then call connect_verify with both. Nothing is charged and no card is needed.
| Name | Required | Description | Default |
|---|---|---|---|
| Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description fully discloses important behaviors: it sends an email, generates a six-digit code valid for 15 minutes, returns a request_id, and does not charge or require a card. This is substantial behavioral context beyond what structured fields 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?
Three concise sentences with no wasted words. The action is front-loaded, the flow is clear, and every sentence contributes essential procedural or safety 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 simple one-parameter tool with no output schema and no annotations, the description covers the input, the outcome, the timeout, the returned request_id, and the next step. An agent has enough information to invoke it correctly without further clarification.
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 schema only lists 'email' with no description, while the tool description adds that it should be the user's work email. This provides meaningful semantic guidance for the single parameter, partially compensating for the 0% schema coverage.
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 begins authentication by sending the user's work email, which is a specific verb and resource. It also differentiates itself from its sibling connect_verify by naming it explicitly and describing the flow.
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 explains when to use this tool: to start authentication. It also explicitly instructs the agent to call connect_verify with both the code and request_id afterward, providing clear sequential guidance and distinguishing from the alternative.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool has a distinct purpose: authentication phases (connect_start/connect_verify), search (search_opportunities), detail retrieval (get_opportunity), workflow navigation (list_workflows/get_workflow), and account status (whoami). No two tools overlap in what they return or the action they perform.
Most names follow a clear lower_snake_case verb_noun pattern: get_opportunity, get_workflow, list_workflows, search_opportunities. The connect_* pair reverses the expected verb order (connect_start rather than start_connect), and whoami is an out-of-pattern Unix-style command, but overall the naming is predictable.
Seven tools is well-scoped for this server's purpose: two for authentication, two for searching/viewing opportunities, two for workflow guidance, and one for account state. Every tool has a clear job and none feel redundant.
The core surface covers authentication, searching, opportunity details, and workflow guidance. However, both search_opportunities and get_opportunity explicitly direct the agent to read_document for document contents, and no such tool is present in the set, creating a notable dead end for eligibility text and tender documents.