Pull one versioned verdict object by tender id (decision, score, per-channel evidence, price status, reason). Requires an API key (Authorization: Bearer cfm_live_…) with an active TendFeed subscription; without one you get a machine-readable key-required or subscription-required answer. Data/research tool over TED (Tenders Electronic Daily, CC BY 4.0). No guarantee of award.
| Name | Required | Description | Default |
|---|---|---|---|
| tender_id | Yes | Tender publication id |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate readOnly and non-destructive; description adds authentication requirements, error responses, data source attribution, and a disclaimer about award guarantee. No contradiction with 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?
Two concise, front-loaded sentences that efficiently convey purpose, prerequisites, and constraints without wasted words.
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 single-parameter tool, the description covers what it returns, authentication, data source, and limitations. No output schema needed; completeness is high.
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% and description repeats the parameter's purpose. No additional semantic detail beyond what the schema provides.
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 pulls a single versioned verdict object by tender ID, listing specific fields (decision, score, etc.). Distinguishes from sibling tools like search_tenders and lane-finding 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?
Specifies required API key and subscription, and behavior when missing. Provides context on data source (TED) and disclaimer. Implicitly differentiates from siblings through focus on single verdict retrieval.
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.
Two tools (find_low_competition_lanes and find_winnable_lanes) are explicitly identical, with the latter deprecated. This creates confusion for an agent trying to select the correct tool, despite the deprecation note. The other two tools are distinct.
Tool names follow a verb_noun pattern (find_*, get_*, search_*), but find_winnable_lanes is a deprecated alias with a name that implies a win forecast, which contradicts its actual function. This inconsistency reduces clarity.
Four tools is well-scoped for a server focused on EU tender analysis and competition detection. Each tool serves a clear purpose, and the count feels appropriate for the domain without being excessive or insufficient.
The tool set covers the core workflow: identifying low-competition lanes, searching tenders with verdicts, and retrieving detailed verdicts. Minor gaps exist (e.g., no raw tender search without verdict), but overall the surface is sufficient for its research purpose.