get_workflowThe complete step-by-step playbook for one workflow id, including the decision gates, the EU procurement specifics that decide eligibility, and the pitfalls that lose bids. Follow it rather than summarising it.
| Name | Required | Description | Default |
|---|---|---|---|
| id | No | ||
| name | No | ||
| workflow_id | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden, and it does add meaningful behavioral context: the output is a full procedural playbook, not a summary, and the agent should follow it. However, it does not disclose behavior around ambiguous optional identifiers, what happens when no identifier is provided, error cases, or whether this is a pure read operation beyond what the name implies.
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 compact and front-loaded with the core purpose. The final instruction to follow rather than summarize earns its place by shaping agent behavior, and there is no redundant or filler language.
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 tool has three optional params, no output schema, and no annotations, so the description must cover both selection semantics and expected results. It ably describes the nature of the returned playbook but omits how to identify the workflow correctly, leaving a meaningful gap 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 description coverage is 0%, so the description needed to compensate, but it only mentions 'one workflow id' without explaining the relationship among the three parameters: id, name, and workflow_id. It does not say which parameter to prefer, how they interact, or what happens when multiple or none are supplied, leaving genuine ambiguity.
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 uses a specific verb and resource: it returns "the complete step-by-step playbook for one workflow id" and details what it contains (decision gates, EU procurement specifics, pitfalls). This clearly separates it from sibling list_workflows, which would provide an overview rather than the full playbook.
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 useful instruction on how to treat the result ('Follow it rather than summarising it'), and the 'one workflow id' phrasing implies a single-workflow lookup. However, it does not explicitly state when to choose this over siblings like list_workflows or search_opportunities, nor does it describe any exclusions or prerequisites.
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 clearly bounded job: auth start/verify, search vs. full record, workflow list vs. workflow detail, and account status. An agent is unlikely to confuse any two tools because resource and action boundaries are distinct.
Six tools follow a consistent lowercase verb_noun pattern: connect_start, connect_verify, get_opportunity, get_workflow, list_workflows, search_opportunities. The exception is 'whoami', a single recognizable token that breaks the verb_noun pattern but is still consistent in style.
Seven tools is well-scoped for an auth-gated EU tender and grant search service. There is no redundancy, and each tool serves a necessary part of the workflow from authentication through search, retrieval, playbooks, and account limits.
The documented workflow is search_opportunities → get_opportunity → read_document, but read_document is absent from the exposed toolset despite being described as the required follow-up for eligibility text. This creates a dead end that will cause agent failures in the core use case. The rest of the surface—search, detail retrieval, workflow guidance, and account introspection—is otherwise reasonably complete.