Bid/no-bid verdicts for open EU tenders, from 592,000 real TED contract awards.
Scored across 4 tools
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.
Rank CPV sector "lanes" by OBSERVED competition density from the full corpus of 530,000 real EU awards: median bidders, single-bidder share, bid-rate, median value, beachhead score. Answers "where is competition thinnest right now". It does NOT estimate the user's probability of winning — thin competition is a selection signal, not a win forecast. Returns the top-ranked lanes only (see "limit"); the total count is in coverage.lanes_ranked. Data/research tool over TED (Tenders Electronic Daily, CC BY 4.0). No guarantee of award.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | How many top-ranked lanes to return (sorted by beachhead_score) | |
| min_n | No | Drop lanes thinner than this (honest: small n = noise) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and destructiveHint, so the safety profile is clear. The description adds crucial context: it's a data/research tool over TED, no guarantee of award, returns only top lanes, and includes total count in coverage. No contradictions.
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 a single paragraph with no fluff. It front-loads the action and then explains scope and limitations. Every sentence serves a purpose. Could be slightly more structured but is efficient.
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 no output schema, the description only vaguely indicates the return (top-ranked lanes, total count in coverage.lanes_ranked). It mentions metrics but not the exact output structure. More detail on return format would improve completeness.
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% and the description adds value by explaining the purpose of min_n ('Drop lanes thinner than this (honest: small n = noise)') and the limit's role. This enriches understanding beyond the 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?
The description uses a specific verb ('Rank CPV sector lanes') and clearly states the resource and metrics. It distinguishes from siblings by explicitly noting it does not estimate win probability, differentiating from find_winnable_lanes.
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 tells when to use the tool ('where is competition thinnest right now') and what it does NOT do (win forecast), helping avoid misuse. It does not explicitly mention alternative tools or when to use them, but the contrast with win probability is strong guidance.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
DEPRECATED — use find_low_competition_lanes instead; this alias behaves identically and stays available for existing clients. The old name wrongly implied a win forecast: TendFeed measures observed competition density, not the probability that you win. Data/research tool over TED (Tenders Electronic Daily, CC BY 4.0). No guarantee of award.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | How many top-ranked lanes to return (sorted by beachhead_score) | |
| min_n | No | Drop lanes thinner than this (honest: small n = noise) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds critical behavioral context: deprecation, identical behavior to replacement, measured competition density not win probability, data source and no guarantee. This far exceeds what 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 concise and front-loaded with the deprecation warning. Every sentence adds value: deprecation, reorientation, correction of misconception, data provenance, and disclaimer. No fluff.
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 data retrieval tool with two well-documented parameters and clear annotations, the description covers purpose, deprecation, behavioral nuance, and limitations. Return values are trivial (list of lanes), so no output schema needed.
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% (both parameters have descriptions). The description does not add extra detail about the parameters themselves, so 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?
The description clearly states the tool is deprecated and points to the replacement find_low_competition_lanes. It explains the actual function (measuring competition density) and corrects the misleading name, distinguishing it from other sibling 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?
Explicitly instructs to use find_low_competition_lanes instead, and clarifies when not to trust the name (win implication). Provides context on data source and constraints, offering clear guidance on usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
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 readOnlyHint=true and destructiveHint=false. The description adds valuable context: authentication failure behavior ('machine-readable key-required or subscription-required answer'), data source (TED with CC BY 4.0), and a disclaimer ('No guarantee of award').
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 front-loaded with the primary purpose, followed by prerequisites, data source, and disclaimer. It is informative without being overly verbose, though the final sentence 'No guarantee of award' is somewhat extraneous given the tool's read-only nature.
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 single-parameter read-only tool with good annotations, the description covers purpose, auth requirements, failure modes, and data provenance. It lacks details about response format, but since no output schema exists, the description could be more explicit about what is returned. Still, it is largely 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?
Schema coverage is 100% with a clear description for 'tender_id'. The description merely echoes 'by tender id' without adding new details about format, validation, or constraints beyond the schema. Baseline 3 is appropriate as the schema already sufficiently explains the 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?
The description clearly states the action ('Pull one versioned verdict object') and the resource ('by tender id'), listing the fields returned (decision, score, per-channel evidence, price status, reason). This distinguishes it from sibling tools that focus on searching or finding lanes/tenders.
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 specifies prerequisites ('Requires an API key with an active TendFeed subscription') and behavior when those are missing. However, it does not explicitly mention when not to use this tool or provide alternatives among siblings, though the context implies it is the sole retrieval tool for verdicts.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Open EU tenders with a bid/no-bid verdict (Worth-It score, reason, competition density, price corridor where robust, deadline, SME-fit). Filter by sector (CPV division), country (NUTS), SME-only, min score. Guests (no key) get the expired-tender board plus a live_matched count; an API key (Authorization: Bearer cfm_live_…) with an active TendFeed subscription unlocks the live, still-biddable board. Data/research tool over TED (Tenders Electronic Daily, CC BY 4.0). No guarantee of award.
| Name | Required | Description | Default |
|---|---|---|---|
| cpv | No | CPV division prefix, e.g. 45 (construction), 72 (IT), 33 (medical) | |
| nuts | No | Country prefix, e.g. DE, FR, PL | |
| limit | No | ||
| sme_only | No | ||
| min_score | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, so the description adds context about the data source (TED, CC BY 4.0), authentication tiers (guest vs. API key), and a disclaimer about no guarantee of award. This goes beyond what annotations provide, but does not cover rate limits or pagination.
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 a single paragraph but packs essential information: purpose, output fields, filters, authentication, and data source. It could be improved by breaking into bullet points for readability, but it is not overly verbose.
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 absence of an output schema, the description reasonably explains what the tool returns (list of tenders with verdict details) and covers authentication differences. However, it omits pagination details and does not mention ordering or other common search parameters, leaving some gaps.
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 input schema already includes descriptions for all 5 parameters, so baseline is 3. The description echoes these filters (sector, country, SME-only, min score) without adding new semantics or usage details for each parameter, so it does not significantly enhance understanding.
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 searches open EU tenders with a bid/no-bid verdict, listing specific output fields like Worth-It score, reason, competition density etc. This distinguishes it from sibling tools like find_winnable_lanes or get_verdict which have different scopes.
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 explains the tool's purpose and notes that guests get expired tenders while API key holders get live ones, but it does not explicitly contrast with sibling tools or specify when not to use this tool. The usage context is implied but not fully directed.
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.
find_low_competition_lanesfind_winnable_lanesget_verdictsearch_tendersEU tenders with no bid, deadlines, competitor maps and company dossiers, dated and stamped.
Search EU public tenders across TED and 8 national portals. Monitor, match, and analyse procurement.
TED MCP Server: Real-time EU public tenders access. https://www.lexsocket.ai/
Tender search + AI CPV finder. Register free: 1 daily email alert, up to 20 results/search.
Add one secure layer between your agents and this server.
