Federal grants and deadlines
Scored across 2 tools
The two tools carve out distinct roles: one searches the live federal listing, the other reads details for a pasted shortlist of IDs. There is minor overlap in that both descriptions mention building a 'grant pipeline tracker' and returning calendar downloads, which could momentarily blur which tool to call for tracking output.
Both names follow the same verb_noun snake_case pattern (find_grant_opportunities, show_grant_details) and clearly encode action plus resource. No mixed conventions.
Two tools is thin for a grant discovery workflow, though the server is explicitly narrow (search + inspect a shortlist). It sits at the borderline where a single extra operation, such as filtering or exporting, would round out the surface.
Search and detail retrieval cover the core read path, but notable operations are absent: no filtering by agency, category, or deadline range, no pagination control, and no persistence of a saved pipeline beyond generated files. Private/state/local grants are deliberately out of scope, so the gap is bounded but real.
Use this when the user wants to find federal grants, search federal grants by eligibility, or build a grant pipeline tracker of open grant opportunities. Queries a live federal listing and returns XLSX and calendar downloads, up to 30 rows per page. Do not use for private foundation, state or local grants.
| Name | Required | Description | Default |
|---|---|---|---|
| page | No | Page number after screening and sorting, e.g. 1; from 1 to 20. | |
| keyword | No | Words to search for, e.g. youth mentoring; quotes are removed. | |
| agencies | No | Department or sub-agency codes, e.g. ["HHS", "DOC-EDA"]. | |
| statuses | No | Notice status, e.g. ["posted"]; defaults to posted and forecasted. | |
| categories | No | Funding categories, e.g. ["ED", "HL"]. | |
| eligibility | No | Applicant types, e.g. ["nonprofit_501c3"]; unrestricted notices are included. | |
| instruments | No | Funding instruments, e.g. ["G"] for grants or ["CA"] for cooperative agreements. | |
| max_results | No | Rows per page, e.g. 25; from 1 to 30. | |
| closing_after | No | Inclusive earliest closing date, e.g. 2026-10-21; defaults to today in America/New_York. | |
| closing_before | No | Inclusive latest closing date, e.g. 2026-12-20; at most 730 days after today. | |
| match_all_words | No | Require all keyword words, e.g. true; default false matches any word. | |
| posted_within_days | No | Number of days since posting, e.g. 7 for a weekly scan. | |
| include_no_close_date | No | Keep rolling or undated notices, e.g. true; default true. |
| Name | Required | Description |
|---|---|---|
| page | Yes | |
| rows | Yes | |
| shown | Yes | |
| errors | Yes | |
| source | Yes | |
| matched | Yes | |
| summary | Yes | |
| has_next | Yes | |
| downloads | Yes | |
| calendar_events | Yes | |
| total_available | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive, open-world. The description adds real value beyond them: live data source, XLSX and calendar download artifacts, and a 30-row page ceiling. It omits rate limits or what happens at page 20+ / empty results, which would be the extra step to a 5.
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?
Two sentences with the trigger, exclusion, and output behavior front-loaded; every clause earns its place and nothing is redundant with the schema.
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 13-parameter, zero-required, open-world search tool with an output schema present, the description is sufficient to call correctly: scope, exclusions, page size, and downloadable outputs are all stated. Return shape and pagination edge behavior are covered by the output schema and schema constraints respectively.
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% with per-parameter examples and constraints, so the schema carries the full burden. The description references 'by eligibility' but adds no constraints, defaults, or interactions between the 13 filters beyond what the schema already states.
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+resource ('find federal grants', 'search federal grants by eligibility') and scopes it to a live federal listing. It does not name the sibling show_grant_details, so the search-vs-details distinction must be inferred, keeping it just short of a 5.
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 opens with an explicit trigger ('Use this when the user wants to...') and includes a clear exclusion ('Do not use for private foundation, state or local grants'). It lacks explicit routing to the sibling tool for detail lookups, so 4 rather than 5.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Use this when the user has federal grant opportunities to review, wants grant deadlines, or needs a grant deadline calendar and grant pipeline tracker for a pasted shortlist. Reads up to 20 opportunity numbers or IDs from the live federal listing. Do not use for grant applications or submitting proposals.
| Name | Required | Description | Default |
|---|---|---|---|
| opportunities | Yes | Opportunity numbers or numeric IDs, e.g. ["2026-NTIA-TBCP", "359145"]. |
| Name | Required | Description |
|---|---|---|
| page | Yes | |
| rows | Yes | |
| shown | Yes | |
| errors | Yes | |
| source | Yes | |
| matched | Yes | |
| summary | Yes | |
| has_next | Yes | |
| downloads | Yes | |
| calendar_events | Yes | |
| total_available | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=true, so the safety profile is fully covered by structured data. The description adds that the source is a 'live federal listing' and a batch ceiling, both useful. It says nothing about behavior for invalid or unknown IDs (error vs. partial results), which is the main remaining uncertainty for a batch lookup.
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?
Front-loaded with the trigger condition, which is good, but the first sentence is keyword-stuffed ('grant deadline calendar and grant pipeline tracker') in a way that reads as search-optimization rather than agent instruction. The second sentence carries the real operational content; the whole thing could be tightened to two lean sentences.
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 rich annotations, a fully documented single parameter, and an output schema that carries the return shape, the description only needs to cover when to call, the batch limit, and the exclusion — all present. Missing only the discovery-vs-lookup alternative and handling of unresolvable IDs.
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 schema already documents the array, its 1-20 bounds, and gives example values ('2026-NTIA-TBCP', '359145'). The description restates the 20-ID cap and the accepted identifier types, corroborating but not extending the schema. Baseline 3 for a fully documented single 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 states a concrete operation on a concrete resource: read details for up to 20 opportunity numbers/IDs from the live federal listing. It implies the payload is deadline/shortlist-review oriented, though it never plainly says what fields come back (deadlines, amounts, eligibility). Clear enough to distinguish from a discovery search, but the resource-level scope is only reached through the trigger phrasing rather than a direct definition.
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?
Explicit trigger conditions are given ('user has federal grant opportunities to review, wants grant deadlines...a pasted shortlist') plus an explicit exclusion ('Do not use for grant applications or submitting proposals'). What's missing is routing to the sibling: it never names find_grant_opportunities as the tool for discovering opportunities the user does not already have IDs for.
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_grant_opportunitiesshow_grant_detailsFederal rules and deadlines
Federal award market reports
Search Grants.gov funding opportunities and read full records: eligibility, awards, deadlines.
Search open and upcoming US federal grant opportunities on Grants.gov and get full grant details.
Add one secure layer between your agents and this server.