Skip to main content
Glama

FundingLandscape

by io.github.tettertotter

Batch Search Contracts

batch_search_procurement
Read-onlyIdempotent

DEPRECATED ALIAS — prefer search_procurement with a queries[] array, which now runs the identical batch fan-out. Kept for backward compatibility; behavior is unchanged. Search federal contracts (SAM.gov) comprehensively. Returns 10 results by default (~4KB). Use detail_level and max_results to control response size. Response includes total available count so you can request more if needed. When sam_filters.pop_state (alias: place_of_performance_state) is set, the response includes a placeOfPerformance field summed across every sub-query (matched, unknownServed with unknowns excluded instead when user_context.location_strict is true, and otherStateExcluded). Counts toward your monthly searches. A batch counts as 1 call.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sinceNoStateless alternative to posted_within_days/new_within_days: ISO 8601 instant. Only opportunities ingested at/after this instant.
offsetNoNumber of results to skip for pagination (default: 0). Use with max_results to page through large result sets. Example: offset=100 with max_results=100 returns results 101-200.
sourceNoFilter every batch sub-query to a specific source/domain, e.g. "sam.gov".
queriesYesArray of 2-5 search queries to run in parallel. Example for IT services: ["IT services contract", "software development federal", "technology consulting government", "computer services procurement"]
max_resultsNoMaximum opportunities to return (default: 10, max: 100). Token cost guide: 10 results ~4KB, 25 results ~10KB, 50 results ~20KB, 100 results ~40KB.
sam_filtersNoSAM.gov specific filters
detail_levelNoControls response verbosity. minimal (~120 bytes/result): id, title, org, deadline, url, qualityScore - best for scanning 50+ results. compact (~400 bytes/result, DEFAULT): adds snippet, category, status, deadlineType, daysUntilDeadline, deadlineLabel, and lastRoundClosedAt - good for recommendations. full (~1.5KB/result): everything including eligibility, amounts - only use with max_results <= 10.compact
user_contextNo
new_within_daysNoBackwards-compatible alias for posted_within_days. Only opportunities ingested (added by us) in the last N days -- for recurring/delta checks ("what is new since my last check"). Applied per sub-query before dedupe; response includes deduped newSince.newCount and the newest/oldest ingest timestamp in the window.
posted_within_daysNoPreferred alias for new_within_days: only opportunities ingested (added by us) in the last N days. Applied per sub-query before dedupe; the response includes a deduped newSince summary. If both posted_within_days and new_within_days are supplied, posted_within_days wins.
max_response_tokensNoToken budget for response (default: 4000 ≈ 16KB). Server auto-caps results to fit. Increase to 8000-16000 for more results per call, decrease to 2000 for lightweight scanning.

TDQS

A4.7/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already mark the tool read-only, idempotent, and non-destructive; the description adds substantial behavior beyond that: default ~4KB/10 results, detail_level and max_results trade-offs, total available count, the placeOfPerformance aggregation semantics under pop_state and location_strict, and monthly search quota impact. No statement contradicts the annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The most important routing information (deprecation and preferred alternative) is front-loaded, followed by the core action, then behavior and cost. The prose is dense, with the pop_state explanation and quota note adding complexity, but no true filler; it is longer than minimal but proportional to an 11-parameter, no-output-schema tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no output schema, the description covers the main invocation risks: deprecated status, response size, count of results, ability to request more, a subtle placeOfPerformance behavior, and quota cost. It does not enumerate the full result payload, but the schema's detail_level descriptions fill that gap, so it is complete enough for correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 91%, so the per-parameter descriptions carry most of the semantic burden. The tool description adds cross-parameter value by tying detail_level/max_results to response size and by explaining the response-shaping effect of sam_filters.pop_state/place_of_performance_state and user_context.location_strict.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description leads with an explicit self-identification as 'DEPRECATED ALIAS' of search_procurement and then states a concrete action and resource: 'Search federal contracts (SAM.gov) comprehensively.' The batch fan-out over queries[] gives a clear behavioral boundary that distinguishes it from the one-query search_procurement sibling.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly directs the agent to 'prefer search_procurement with a queries[] array' and says this tool is 'Kept for backward compatibility,' which is an unambiguous when-not-to-use instruction. It also supplies operational usage context such as response-size controls and monthly quota counting.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All FundingLandscape toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.1/5.0
Disambiguation4/5

Most tools have clear distinct purposes. Some overlap exists (e.g., search_grantsplus and search_foundations both return foundations, but descriptions clarify the distinction). Also batch_ variants are comprehensive versions of the standard searches. Overall, agents can differentiate well.

Naming Consistency4/5

Tool names predominantly follow verb_noun pattern in snake_case (e.g., search_grantsplus, get_opportunity, list_saved_searches). Minor deviation with 'whats_new' (no underscore) and 'check_connection' (different verb form). Otherwise consistent.

Tool Count4/5

26 tools is slightly above the typical 3-15 range but still reasonable for a comprehensive funding landscape server covering grants, procurement, foundations, saved searches, account management, and utilities. Each tool serves a clear purpose.

Completeness4/5

The tool surface covers core search, detail retrieval, saved search management, account information, and feedback. Missing are profile management or direct payment modification tools (only links provided). Minor gaps but overall complete for the domain.

Resources