Skip to main content
Glama

What's New

whats_new
Read-onlyIdempotent

DEDICATED "what's new since I last checked" tool for recurring agent checks: one obvious call instead of remembering the new_within_days param on a search tool. Returns opportunities FundingLandscape ingested in the last N days (default 7), with a newSince summary (newCount, newest, oldest ingest timestamp). In a pure recency digest without a single source, the window is sampled across sources round-robin by ingest recency so one bulk harvester cannot own the digest; each source remains newest first. In windowCoverage, sourcesSampled counts distinct sources returned by the grouped provider query before MCP quality, judge, recency-withhold, and page filters; it is absent when no grouped sample was available, including when sampling was not attempted, and 0 means the grouped query succeeded but returned no sourced rows; sourcesServed counts distinct sources delivered on this page. windowCoverage.order is "recency" for the queryless browse digest or "relevance" when a query is present. windowIncomplete/incompleteReason reports any incomplete retrieval walk, and ceilingTruncated is true only when the 2,000-row ceiling excluded records; ceilingTruncated and hardCeiling are present only when order is "recency" and are omitted entirely under "relevance" (query mode never walks past a single bounded fetch, so no ceiling logic runs). Wraps the same ingest-freshness filter as posted_within_days/new_within_days on the search tools, no separate counting logic. Optional query/status/source narrow the window; omit query entirely for a pure recency digest across everything new. For a stateless watermark, pass since (ISO 8601) instead of days, then store this response's newSince.newest and pass it back next time. Free tier: full window, honest held-back count if the recency gate withholds anything newer. Counts toward your monthly searches.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
daysNoIngest-freshness window in days (default: 7). Only opportunities FundingLandscape ADDED in the last N days, not the opportunity posted date or deadline. Ignored if since is set.
limitNoResults per page (default and maximum: 25). Large results produce smaller pages; follow nextCursor even after a short page.
queryNoOptional natural language filter (e.g. "clean energy nonprofit"). Omit for a pure recency digest across all new opportunities.
sinceNoStateless alternative to days: ISO 8601 instant. Only opportunities ingested at/after this instant. Store the previous response newSince.newest and pass it here to manage your own watermark.
cursorNoPagination cursor from previous response
sourceNoFilter to a specific source/domain, e.g. "grants.gov" or "sam.gov".
statusNoFilter by opportunity status (default: active)
compactNoReturn compact results (default: true). Set to false for full details.
categoryNoFilter by category
min_qualityNoMinimum record-completeness tier (default: medium). any removes this quality-tier filter; relevance, access and other filters still apply.
user_contextNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / min_quality / description
      Previous value: -"Minimum quality threshold (default: medium)"New value: +"Minimum record-completeness tier (default: medium). any removes this quality-tier filter; relevance, access and other filters still apply."
  2. Changed1 schema field changed
    • changedInput schema / properties / limit / description
      Previous value: -"Max results (default: 25)"New value: +"Results per page (default and maximum: 25). Large results produce smaller pages; follow nextCursor even after a short page."
  3. Added

TDQS

A4.8/5.0
Behavior5/5

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

Even with readOnly/idempotent annotations, the description discloses substantial non-obvious behavior: round-robin sampling so one bulk harvester cannot own the digest, the meaning of `windowCoverage.sourcesSampled` absent vs. 0, `ceilingTruncated` only appearing in recency mode, and the honest held-back count under the free tier. This goes well beyond 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 description is long, but it is front-loaded with the core purpose and then structured around genuinely important behavioral edge cases that are not visible in the schema or annotations. Each sentence adds operational value, though the density around `windowCoverage` semantics makes it heavier than a minimal description would be.

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

Completeness5/5

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

There is no output schema, so the description carries the burden of explaining return semantics. It covers `newSince`, `windowCoverage`, `sourcesServed`, `windowIncomplete`/`incompleteReason`, `ceilingTruncated`/`hardCeiling`, ordering behavior in both recency and relevance modes, and free-tier behavior. That is sufficient for an agent to invoke and interpret the tool correctly.

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 high at 91%, so the baseline is 3, and the description adds extra meaning on top: `since` is the stateless alternative to `days`, `omit query entirely` for a pure digest, and `newSince.newest` is the value to reuse as the next watermark. It doesn't enumerate every parameter, but the schema already covers those details.

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 opens by naming the tool's specific role: a dedicated 'what's new since I last checked' tool for recurring agent checks, and then states it 'Returns opportunities FundingLandscape ingested in the last N days (default 7), with a newSince summary.' It also differentiates itself from the search siblings by framing itself as the alternative to 'remembering the new_within_days param on a search tool.'

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?

Usage is explicitly contextualized: use this tool instead of the search tools' new_within_days/posted_within_days parameter, and 'omit query entirely for a pure recency digest across everything new.' It also gives concrete stateless-watermark instructions: pass `since` (ISO 8601), store the response's `newSince.newest`, and pass it back next time.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources