Revly

Hent granskningsfunn fra Revly

hent_funn

Read-onlyIdempotent

Henter granskningsfunn på én eksplisitt oppdrags-ID: kode, tittel, beløp, merking, status, gjeldende vurdering, spor og kildens etikett med revly_url. Dette er ikke feilinformasjonspostene i funn_rad og ikke antallene i activity.funn på hent_oppdrag_tilstand, som er feilinformasjon. Et innebygd agentverktøy med samme navn leser et annet register. Lang beskrivelse er utelatt. Fortrolige funn er med og merket fortrolig. «Mangler kilde» betyr at kilden mangler, aldri at funnet er i orden. Filteret vurdering lik ikke_vurdert tar også med funn uten vurderingsrad. Høyst 80 funn og 20 kilder per funn.

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": {
      "oppdrag_id": "<oppdrag_id>"
    },
    "name": "hent_funn"
  }
}

Input Schema

Name	Required	Description
`merking`	No	Merking av kilden til funnet.
`spor_id`	No	Bare funn i dette sporet.
`vurdering`	No	Gjeldende vurdering. ikke_vurdert tar også med funn uten vurderingsrad.
`oppdrag_id`	Yes	Eksplisitt oppdrags-ID fra Revly. Oppslag uten ID er ikke tillatt.
`endret_siden`	No	Bare funn endret, eller vurdert, etter dette tidspunktet.
`mangler_kilde`	No	true: bare funn uten kilde. false: bare funn med minst én kilde.

Output Schema

Name	Required	Description
`funn`	No	Granskningsfunn, at most 80.
`status`	Yes	Result status. not_found_or_unavailable means the engagement is not visible to this connection and the call is an error.
`sources`	No	Sources that contributed to the result.
`evidence`	No
`revly_url`	No	Link to the granskningsfunn page.
`truncated`	No	True when findings or their sources were cut.
`oppdrag_id`	No	Engagement ID, as text.
`funn_antall`	No	Matching findings. Zero is an empty register, not an unavailable one.
`operation_id`	Yes	Revly operation ID for this read, recorded in the access log.
`missing_sources`	No	Sources with no record. Missing data stays visible and is never treated as a positive result.
`inneholder_fortrolig`	No	True when any matching finding is marked confidential, including rows past the cap.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 2, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, yet the description adds real context: confidential findings are included and flagged, results are capped at 80 findings and 20 sources per finding, and 'mangler kilde' is defined as a missing source rather than a clean finding. These are meaningful behavioral disclosures 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.

Conciseness3/5

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

The returned-field list and the sibling disambiguation are front-loaded and useful, but the sentence 'Lang beskrivelse er utelatt' is wasted meta-commentary that earns no place, and the paragraph is dense with several distinct facts packed together.

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?

With an output schema present, return values need not be explained, and the description still covers confidentiality, result caps, and filter edge cases. It is nearly complete for a read-only filtered-list tool; only the exact alternative tool for the ruled-out cases is left implicit.

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 100%, so baseline is 3, but the description adds semantics the schema does not: vurdering=ikke_vurdert also includes findings with no assessment row, and mangler_kilde is clarified as source-absence. This meaningfully enriches two of the six parameters.

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?

States a specific verb (Henter) and resource (granskningsfunn) scoped to one explicit oppdrag-ID, and enumerates the returned fields (kode, tittel, beløp, merking, status, vurdering, spor, revly_url). It explicitly distinguishes itself from funn_rad and from activity.funn on hent_oppdrag_tilstand, so an agent can tell it apart from siblings without opening schemas.

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

Usage Guidelines4/5

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

Clearly signals when this is the right tool by ruling out the misinformation entries in funn_rad and the counts in hent_oppdrag_tilstand, and notes a same-named built-in agent tool reads a different register. It stops short of naming the exact sibling to use instead for those other cases, so it is strong but not fully prescriptive.

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

All Revly tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?