Skip to main content
Glama

What changed in the notice record

compare_notice_record_versions

Not affiliated with the U.S. government, GSA, or SAM.gov. Not a U.S. government service. Compares recorded notice facts with the baseline identified by a receipt previously returned by get_notice_record. The receipt must belong to the same caller and must not be expired. Reports source-supported fact changes and whether the supplied comparison filters changed; it does not compare or generate model estimates. Creates a new private comparison receipt, with the exact UTC expiry shown in expires_at. An empty changed_facts array means that no recorded fact changes were found against that baseline. Does not recommend bids, determine eligibility, or suggest partners. Follow-ups within 30 minutes after a search ride free (up to 30 per search); otherwise one accepted call counts as one use. Without a connected GovInbox account, both limits apply: 3 searches per UTC calendar day and 10 per UTC calendar month. With a connected GovInbox account, the limit is 20 searches per UTC calendar month, with no separate daily limit. One accepted search counts as one use, regardless of the number of records returned. Follow-up calls (opening records, comparing versions, listing awards or subawards) within 30 minutes after a search do not count extra, up to 30 follow-ups per search. A follow-up invoked with no active search window counts as one use and opens a new 30-minute window. Empty results consume the search. A lookup for a record that does not exist is not charged. Each retry of a search counts as a new search, as does each call for another page of search results. Daily limits reset at 00:00 UTC each day; monthly limits reset at 00:00 UTC on the first day of each month. Requests rejected for invalid authentication or an exhausted quota do not consume a use.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "prior_receipt": "<prior_receipt>"
    },
    "name": "compare_notice_record_versions"
  }
}

Input Schema

NameRequiredDescriptionDefault
notice_idNoNotice id; defaults to the receipt's notice
prior_receiptYesreceipt_id from a get_notice_record result
search_filtersNoSame filters as get_notice_record; supply them again to detect input changes

Output Schema

NameRequiredDescriptionDefault
quotaYes
notice_idYes
new_receiptYes
sam_gov_urlNoDeep link to the notice on SAM.gov for verification
changed_factsNo
inputs_changedYes
prior_receipt_idYes
analytical_disclaimerYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changed
    • addedOutput schema / $defs / StatementSource / properties / calculated_at
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "UTC time a derived statement was calculated; not source retrieval",
      +  "title": "Calculated At"
      +}
    • addedOutput schema / $defs / StatementSource / properties / query_time
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "UTC time this stored-data query was evaluated; not source freshness",
      +  "title": "Query Time"
      +}
    • addedOutput schema / $defs / StatementSource / properties / retrieved_at / anyOf
      Added value: +[
      +  {
      +    "type": "string"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • addedOutput schema / $defs / StatementSource / properties / retrieved_at / default
      Added value: +null
    • changedOutput schema / $defs / StatementSource / properties / retrieved_at / description
      Previous value: -"UTC ISO 8601 when the source was retrieved"New value: +"Recorded UTC source retrieval time, or null when unknown; never response time"
    • removedOutput schema / $defs / StatementSource / properties / retrieved_at / type
      Removed value: -"string"
    • changedOutput schema / $defs / StatementSource / required
      Previous value: -[
      -  "system",
      -  "record_id",
      -  "retrieved_at"
      -]New value: +[
      +  "system",
      +  "record_id"
      +]
  2. Changed7 schema fields changed
    • removedOutput schema / $defs / StatementSource / properties / calculated_at
      Removed value: -{
      -  "anyOf": [
      -    {
      -      "type": "string"
      -    },
      -    {
      -      "type": "null"
      -    }
      -  ],
      -  "default": null,
      -  "description": "UTC time a derived statement was calculated; not source retrieval",
      -  "title": "Calculated At"
      -}
    • removedOutput schema / $defs / StatementSource / properties / query_time
      Removed value: -{
      -  "anyOf": [
      -    {
      -      "type": "string"
      -    },
      -    {
      -      "type": "null"
      -    }
      -  ],
      -  "default": null,
      -  "description": "UTC time this stored-data query was evaluated; not source freshness",
      -  "title": "Query Time"
      -}
    • removedOutput schema / $defs / StatementSource / properties / retrieved_at / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • removedOutput schema / $defs / StatementSource / properties / retrieved_at / default
      Removed value: -null
    • changedOutput schema / $defs / StatementSource / properties / retrieved_at / description
      Previous value: -"Recorded UTC source retrieval time, or null when unknown; never response time"New value: +"UTC ISO 8601 when the source was retrieved"
    • addedOutput schema / $defs / StatementSource / properties / retrieved_at / type
      Added value: +"string"
    • changedOutput schema / $defs / StatementSource / required
      Previous value: -[
      -  "system",
      -  "record_id"
      -]New value: +[
      +  "system",
      +  "record_id",
      +  "retrieved_at"
      +]
  3. Changed7 schema fields changed
    • addedOutput schema / $defs / StatementSource / properties / calculated_at
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "UTC time a derived statement was calculated; not source retrieval",
      +  "title": "Calculated At"
      +}
    • addedOutput schema / $defs / StatementSource / properties / query_time
      Added value: +{
      +  "anyOf": [
      +    {
      +      "type": "string"
      +    },
      +    {
      +      "type": "null"
      +    }
      +  ],
      +  "default": null,
      +  "description": "UTC time this stored-data query was evaluated; not source freshness",
      +  "title": "Query Time"
      +}
    • addedOutput schema / $defs / StatementSource / properties / retrieved_at / anyOf
      Added value: +[
      +  {
      +    "type": "string"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • addedOutput schema / $defs / StatementSource / properties / retrieved_at / default
      Added value: +null
    • changedOutput schema / $defs / StatementSource / properties / retrieved_at / description
      Previous value: -"UTC ISO 8601 when the source was retrieved"New value: +"Recorded UTC source retrieval time, or null when unknown; never response time"
    • removedOutput schema / $defs / StatementSource / properties / retrieved_at / type
      Removed value: -"string"
    • changedOutput schema / $defs / StatementSource / required
      Previous value: -[
      -  "system",
      -  "record_id",
      -  "retrieved_at"
      -]New value: +[
      +  "system",
      +  "record_id"
      +]
  4. Changed1 schema field changed
    • addedOutput schema / $defs / QuotaBlock / properties / mode
      Added value: +{
      +  "default": "ordinary",
      +  "enum": [
      +    "ordinary",
      +    "testing",
      +    "review",
      +    "beta"
      +  ],
      +  "title": "Mode",
      +  "type": "string"
      +}
  5. First observed

TDQS

B3.4/5.0
Behavior4/5

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

Annotations declare readOnlyHint=false, idempotentHint=false, and openWorldHint=true; the description explains why mutation occurs (a new private comparison receipt is created, with the exact UTC expiry shown in expires_at) and clarifies the key semantic that an empty changed_facts array means no changes were found. It also discloses quota and follow-up-window costs. Points deducted because the quota block reads like boilerplate copied from search tools – it talks about 'searches' rather than comparisons and repeats the same rule twice, muddying rather than clarifying how this specific tool is metered.

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

Conciseness2/5

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

The core comparison semantics are buried under a long disclaimer and a bloated quota paragraph that restates the same rules twice ('One accepted search counts as one use' and the 30-minute follow-up window each appear more than once). The meter text also references searches in a way that is confusing for a comparison tool. Not front-loaded: the lead sentence is legal boilerplate, not purpose.

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

Completeness3/5

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

An output schema exists and annotations are present, so return-shape and safety burden is partly covered. The description covers the empty-result case and receipt lifecycle, which matters. But it leaves ambiguity about what constitutes a 'source-supported fact change' and blends search-metering rules into a comparison tool, so an agent may misjudge cost and scope.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already documents receipt_id provenance, the notice_id default, and that search_filters are used for input-change detection. The description restates the receipt ownership/expiry constraint and the fact that filters only detect input changes, which is useful reinforcement but adds little beyond the schema. Baseline 3 applies.

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

Purpose4/5

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

States a specific verb and resource: compares recorded notice facts against a baseline identified by a receipt from get_notice_record, and explicitly says it does not compare or generate model estimates. That is clear enough to distinguish it from get_notice_record and check_notice_filters, but the sibling differentiation is implicit rather than named. The opening legal disclaimer occupies prime real estate before the actual purpose.

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

Usage Guidelines3/5

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

Gives prerequisites (the receipt must belong to the same caller and must not be expired) and states what the tool does not do (no bid recommendations, eligibility, or partner suggestions). However, it never says when an agent should choose this over get_notice_record, get_brief, check_notice_filters, or research, and there are 40+ siblings. Usage is implied by the receipt requirement rather than explained.

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