Skip to main content
Glama

Is this injury or illness OSHA recordable?

osha_is_recordable
Read-onlyIdempotent

Decide under 29 CFR 1904.4-1904.11, 1904.29 and 1904.39 whether a case goes on the OSHA 300 Log, its column (death, days away, restricted, other) and type, whether it is a privacy case, and whether OSHA must be called within 8 or 24 hours. First-aid ids: otcMedicationAtOtcStrength, tetanusImmunization, cleaningWounds, woundCoverings, hotColdTherapy, nonRigidSupport, temporaryImmobilizationForTransport, nailDrillingBlisterDraining, eyePatch, eyeForeignBodyIrrigationOrSwab, splinterRemovalSimple, fingerGuards, massage, drinkingFluidsHeatStress. Medical-treatment ids (any other text also counts as medical treatment): prescriptionMedication, sutures, rigidSplintOrCast, physicalTherapy, otherImmunization, eyeForeignBodyOtherMeans, woundClosingDevice, respiratoryTherapy, surgery. Work-relatedness exceptions: generalPublic, symptomsOnly, voluntaryWellness, eatingDrinking, personalTasks, personalGrooming, commuteParkingLot, coldOrFlu, mentalIllnessNoOpinion.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "osha_is_recordable"
  }
}

Input Schema

NameRequiredDescriptionDefault
typeNoinjury, skin, respiratory, poisoning, hearing or other (illness)
deathNoDeath
daysAwayNoCalendar days away from work, not counting the day of injury
diagnosisNoSignificant diagnosis
exceptionNoA 1904.5(b)(2) exception that applies, if any
lossOfEyeNoLoss of an eye
amputationNoAmputation
treatmentsNoTreatments given: first-aid ids, medical-treatment ids, or plain text
mentalIllnessNoMental illness
sexualAssaultNoSexual assault
medicalRemovalNoMedical removal under an OSHA standard
restrictedDaysNoCalendar days of restricted work or job transfer
hivHepatitisOrTbNoHIV, hepatitis or tuberculosis
intimateBodyPartNoIntimate body part or reproductive system
contaminatedSharpsNoNeedlestick or cut from a sharp contaminated with another person's blood or OPIM
hoursAfterIncidentNoHours from the incident to the death, hospitalization, amputation or eye loss
lossOfConsciousnessNoLost consciousness
employeeRequestsPrivacyNoEmployee asked that their name be left off (illnesses only)
inpatientHospitalizationNoIn-patient hospitalization
tuberculosisAfterExposureNoTB infection after occupational exposure to a known active case
bloodborneIllnessDiagnosedNoA bloodborne illness was diagnosed
continuationOfRecordedCaseNoSame type of injury to the same body part, already recorded, not yet healed
preExistingSignificantlyAggravatedNoFor a pre-existing condition: did work significantly aggravate it?

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already establish that this is a read-only, idempotent, non-destructive, closed-world operation. The description adds useful behavioral context by naming the regulatory basis and the specific determinations returned, including log column, privacy case status, and reporting deadlines. It does not describe output format or edge-case behavior, but the annotations lower the burden.

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 front-loaded with the core decision and outputs, then supplies necessary classification lists. It is dense and list-heavy, but the length is justified by the complexity of the regulatory decision and the treatment-ID vocabulary. Minor formatting improvements could help, but there is little wasted wording.

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?

For a 23-parameter decision tool with no output schema, the description is largely complete: it states the regulatory basis, the determinations returned, and the key classification vocabularies. It does not specify the exact response shape, but it describes the substantive outputs well enough for an agent to understand what the tool provides.

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 the schema already documents all 23 parameters. The description still adds meaningful semantics by enumerating first-aid and medical-treatment IDs and clarifying that any other treatment text counts as medical treatment, plus listing work-relatedness exceptions. It does not explain every parameter, but it adds substantial value beyond the schema for the most ambiguous inputs.

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 uses a specific verb, "Decide," and a precise resource: OSHA recordability under cited CFR sections. It also states the decision outputs (300 Log column/type, privacy status, and 8/24-hour reporting), which clearly distinguishes it from sibling tools like osha_coverage or cfr_lookup.

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?

The description makes the tool's role clear as a recordability decision aid and supplies regulatory context, but it does not explicitly say when to use this versus alternatives such as cfr_lookup or osha_coverage. There are no when-not conditions or named alternatives, so usage is implied rather than fully guided.

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.