Limited-beta SAM.gov opportunity research: incumbent evidence, historical awards, comparable obligations and agency spending. One existing tool: getOpportunityIntelligence. Each consumer supplies their own RapidAPI key in x-api-key with entitlement to US Federal Bid Intelligence API. Fixed proxy routing; backend and tool unchanged. BASIC free 50 calls/month; PRO $5/100 calls/month. All consumers share 6 SAM pulls per UTC day; fresh cache valid 24h. No guaranteed fresh-query capacity. Public init
Scored across 1 tool
With only a single tool in the surface, there is no possibility of confusing it with another; its purpose (fetching intelligence for a specific notice ID) is unambiguous.
The lone name uses camelCase with a clear verb_noun structure (getOpportunityIntelligence), which is readable and predictable, though a single tool provides no pattern to validate consistency against.
One tool is too thin for a domain labeled 'Bid Intelligence' — there is no discovery, search, or listing capability, forcing the agent to already know a 32-character notice ID from elsewhere.
The surface is essentially a single lookup keyed by an opaque notice ID with no way to find, search, filter, or enumerate opportunities, so most realistic bid-intelligence workflows dead-end immediately.
Uses a 32-character notice ID. Notices posted within the last year. Cached up to 24 hours; stale snapshots state age. Cold lookups are subject to a conservative shared official-source daily budget. Amounts are obligations, not bid estimates or opportunity budgets.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | 682fe80c17c543e7a5b5ff204ae6687a | |
| _method | No | HTTP method | GET |
| _endpoint | No | Endpoint: GET /opportunity/{id}/intelligence | /opportunity/{id}/intelligence |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does well: it discloses caching semantics (24h TTL, age disclosure on stale snapshots) and a real cost/throttling constraint (conservative shared official-source daily budget) that an agent should factor into call planning. It also corrects a likely misinterpretation of returned amounts (obligations, not bid estimates or budgets). Missing: auth requirements, behavior when the notice is unknown or too old, and what the payload contains.
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?
Four compact sentences, no filler, and the input requirement is front-loaded. The telegraphic fragments ("Uses a 32-character notice ID.") trade some readability for density, but every sentence contributes a constraint the agent needs.
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?
There is no output schema and no annotations, so the description should describe what comes back; it only hints at returned amounts and a snapshot age field. Operational constraints (ID format, recency window, caching, budget) are covered well, but for a tool whose entire value is its data payload, the return shape is left largely unspecified.
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 67% and the description adds meaning the schema does not: that the id is a *notice* ID (the schema only shows a hex pattern) and that only notices from the last year are valid inputs, which materially affects whether a given value will work. This goes beyond the bare pattern constraint. The hidden method/endpoint params need no elaboration.
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 never states what the tool actually does or returns beyond the name's implication; it opens with an input constraint ("Uses a 32-character notice ID") rather than a verb+resource statement. The agent can infer that intelligence for a notice/opportunity is retrieved, but nothing in the text confirms the resource or scope. Sibling tools are absent, so differentiation is not required, but the purpose remains vague.
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 gives operative conditions for when this tool is usable: only notices posted within the last year, cache freshness of up to 24 hours with stale snapshots self-reporting their age, and cold lookups drawing on a shared daily budget. There are no alternatives to route between, so no exclusions are needed. The main gap is that it does not say what to do when the notice falls outside the one-year window.
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.
getOpportunityIntelligence
Add one secure layer between your agents and this server.