Predict federal contract recompetes: expiring contracts, likely competitors, win odds.
Scored across 3 tools
Each tool has a distinct primary purpose: listing expiring contracts, profiling lane competitors, and predicting a specific recompete outcome. There is minor overlap because predict_recompete also returns competitor rankings, but the contract-specific probability focus makes it clearly distinct from lane_competitors.
The naming is readable but inconsistent: expiring_recompetes and lane_competitors are noun phrases while predict_recompete is verb-led. The singular/plural mismatch between 'recompetes' and 'recompete' also adds slight inconsistency.
Three tools is well-scoped for the narrow domain of federal recompete prediction. Each tool covers a core workflow step without unnecessary bloat.
The set covers the essential pipeline: surface expiring contracts, identify likely bidders, and produce a prediction with confidence. Minor gaps exist around inspecting past prediction accuracy or contract-level details, but agents can accomplish the stated purpose without dead ends.
List federal contracts EXPIRING in a horizon window (period-of-performance end), with a winner prediction for each. Filter by NAICS and agency. This is the recompete pipeline feed.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max contracts (default 20). | |
| naics | No | 6-digit NAICS. | |
| agency | No | ||
| maxDays | No | Window ceiling in days (default 180). | |
| minDays | No | Window floor in days (default 90). | |
| minAmount | No | Minimum award $ (default 1,000,000). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description must disclose behaviors. It mentions the data source (period-of-performance end) and that it provides a winner prediction. However, it does not detail how predictions are made, potential rate limits, or whether the operation is read-only (though listing implies read). Adequate but not rich.
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 two sentences, front-loading the core purpose. Every word adds value: 'List', 'EXPIRING', 'horizon window', 'winner prediction', 'Filter by NAICS and agency'. No fluff or redundancy.
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 six parameters and no output schema, the description covers the main purpose and filtering but does not detail default values or the structure of the returned data (e.g., fields like contract ID, amount). It could mention window floor/ceiling explicitly. Still, it provides enough for basic use.
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 83% (only agency lacks description). The description adds meaning by explaining the horizon window concept (min/max days) and filters (NAICS, agency). It reinforces the parameters without repeating schema entirely, providing useful context 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 clearly identifies the tool as listing expiring federal contracts with winner predictions, specifying filtering by NAICS and agency. It distinguishes from sibling tools by calling it 'the recompete pipeline feed', which implies a broad listing versus per-contract prediction.
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 states when to use: to list expiring contracts within a horizon window with predictions. It does not explicitly mention when not to use or alternatives, but the context is clear enough that an agent can infer its use case. Sibling tools are not contrasted, which slightly reduces the score.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return the firms with the most recent award velocity in a NAICS (and optional agency) lane — i.e. the likely bidders on any recompete in that lane, ranked by recent wins and dollars.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Default 15. | |
| naics | Yes | ||
| agency | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, description lacks behavioral details like data recency, caching, authentication, or output specifics beyond ranking. Only discloses purpose and ranking criteria.
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?
Single, well-structured sentence with clarifying clause. Front-loaded verb and resource. No excess verbiage.
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?
Adequate for a list tool with moderate complexity, but missing output shape, limit default behavior, and agency format constraints. No annotations to supplement.
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?
Description adds context to 'naics' and 'agency' parameters by linking them to 'lane', but does not compensate for low schema coverage (33%)—e.g., no format guidance for agency or limit semantics beyond 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?
Clearly states the tool returns firms with award velocity in a NAICS lane, explains what that means (likely bidders), and specifies ranking criteria. Differentiates from siblings by focusing on competitors.
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?
Implicitly suggests use for finding likely bidders in a lane, but no explicit when-to-use vs alternatives like 'expiring_recompetes' or 'predict_recompete'.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Predict WHO will win an expiring federal contract recompete. Pass a contract identifier (USAspending generated_internal_id / award gid) OR a NAICS+incumbent pair. Returns the incumbent with an adjusted incumbent-advantage probability plus top likely competitors ranked by recent award velocity in the NAICS/agency lane, the BASE RATES used, sample size, and an honest confidence band. Probabilistic estimate from PUBLIC USAspending data — not insider info.
| Name | Required | Description | Default |
|---|---|---|---|
| gid | No | USAspending generated_internal_id (award gid). Best input. | |
| topN | No | Number of competitors to return (default 5). | |
| naics | No | 6-digit NAICS, used to build the competitor field (required if no gid). | |
| agency | No | Awarding agency name (optional, sharpens the lane). | |
| incumbent | No | Incumbent contractor name (required if no gid). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully covers behavioral aspects: it is a probabilistic estimate from public data, not insider info, and outputs include base rates, sample size, and confidence band. It does not elaborate on data freshness or specific interpretation of 'honest confidence band', but overall sufficient.
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 sentences, front-loaded with purpose, then input options, then output details. No superfluous text; each sentence adds essential information. Efficiency is optimal.
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 5 parameters, 100% schema coverage, no output schema, the description sufficiently covers inputs and outputs. However, it lacks mention of error handling for invalid contract IDs or edge cases. Overall, substantial but not exhaustive.
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 descriptions for all 5 parameters. The tool description adds value by explaining that 'gid is best input', that 'naics and incumbent are required if no gid', that 'agency sharpens the lane', and that topN has a default of 5 (not in schema). This clarifies usage 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?
Description clearly states the tool predicts recompete winners, specifies inputs (contract ID or NAICS+incumbent pair), and lists outputs (incumbent probability, competitors, base rates, sample size, confidence band). It distinguishes from sibling tools 'expiring_recompetes' (lists contracts) and 'lane_competitors' (lists competitors) by focusing on prediction.
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?
Description provides clear input options: 'Pass a contract identifier ... OR a NAICS+incumbent pair' and indicates 'gid is best input' while 'naics and incumbent are required if no gid'. However, it does not explicitly state when not to use the tool or compare directly with siblings for decision-making.
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.
expiring_recompeteslane_competitorspredict_recompeteFederal contract intelligence: $7T+ awards, SAM.gov opps, pWin verdicts, recompetes, protests.
US federal contract recompetes with the incumbent named, awards by company, agency spend.
Federal sales intelligence: expiring-contract triggers, agency spend intel, deal qualification.
Cassandra prediction hub: one MCP door over govcon forecasts (recompete, contractor signals).
Add one secure layer between your agents and this server.
