GBU Compliance

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

With no annotations, the description carries the full burden, and it does add real value: it names what comes back (risk level per hazard, non-low gaps, next review date) and asserts determinism, which is useful for caching and retry reasoning. However, it never discloses that the call appears to persist a record (the schema says employees are 'stored in the record'), so the write side-effect of this tool is left unstated.

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?

Three short sentences, zero filler, and the core purpose is front-loaded before the return-value and determinism details. Every sentence earns its place.

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?

No output schema exists, and the description does the right thing by summarizing the return shape and determinism. The remaining gap is the undisclosed persistence of the record and the list_hazards prerequisite, but the essentials for calling it correctly are present.

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 each of the three parameters documented in the schema itself, so the baseline is 3. The description adds no syntax, format, or constraint detail beyond the schema's own parameter docs.

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?

States a specific verb (assess) and resource (a workplace) against a named standard, section 5(3), which pins down what the operation means. It is distinguishable from siblings like list_hazards or review_due by the assessment framing, though it never explicitly contrasts itself with them.

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?

The description implies when this is used (assessing a workplace against the hazard checklist) but gives no explicit trigger conditions, no when-not guidance, and no mention of prerequisites. The dependency on list_hazards for hazard IDs only appears in the schema, not the description.

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

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

No annotations are provided, so the description carries the full burden. It says what fields are returned but never clarifies whether the record is persisted, whether this is a read-only computation, or whether it is idempotent. The core behavioral question for a 'build' tool is unaddressed.

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 tight sentences with the purpose front-loaded and no filler. The second sentence is largely a restatement of the first's return content, so it earns slightly less than a perfect score.

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 3-parameter tool with no output schema and no annotations, the description names the returned fields but omits the required 'hazards' input, the meaning of 'sector', and any persistence behavior. It is minimally adequate but leaves clear gaps.

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 67%, below the 80% baseline, and the description mentions no parameters at all. It never explains the required 'hazards' input, its linkage to list_hazards, or the undocumented 'sector' field, so it adds no meaning beyond the schema.

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?

States a specific verb ('Build') and a precise resource ('section 6 ArbSchG documentation record for an assessment'), and clarifies the output ('result, measures and the review result field'). It does not, however, explicitly contrast itself with siblings like assess_workplace or review_due, leaving the boundary to inference.

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?

The phrase 'for an assessment' implies the tool is used in the context of an assessment, but there is no explicit when-to-use, prerequisite ordering, or named alternative. Usage is only implied, not stated.

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

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

With no annotations, the description carries the full behavioral burden. It discloses the return structure (results grouped into six statutory categories) and the dependency relationship to assess_workplace, which is meaningful given there is no output schema. It stops short of stating that the list is static/exhaustive or noting any permission or rate-limit behavior, so it is not complete.

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, zero filler, and the purpose/grouping is front-loaded before the next-step instruction. Every clause earns its place.

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 zero-parameter, no-output-schema read tool this covers purpose, result structure, and the follow-up step. What is missing is minor: whether the checklist is fixed or configurable, and whether the six-category grouping is exhaustive.

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?

The tool takes zero parameters, so per the baseline the schema carries no semantics to explain. The description correctly adds no parameter prose because none is needed, and instead spends its words on output shape and workflow.

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?

States a specific verb (List) and resource (hazard checklist) and anchors it to a concrete domain artifact (Gefährdungsbeurteilung) plus the statutory grouping (ArbSchG §5(3)). It explicitly distinguishes itself from the sibling assess_workplace by naming it.

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?

'Read this first, then pick IDs for assess_workplace' gives an explicit ordering and names the downstream tool, so an agent knows both when to call it and what to do with the result. No exclusions are stated, but the workflow routing is unambiguous.

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

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

No annotations are provided, so the description carries the full burden. It helpfully discloses the actual computation rules (high=180, medium=365, low=730 days), which is real behavioral value, but it says nothing about the return format, the base date that 'next' is measured from, or whether the call has any side effects.

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?

One front-loaded sentence with zero filler; the action, the input, and the output mapping are all packed in without waste.

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 single-parameter pure lookup this is close to adequate, and the value-to-days mapping is complete. Gaps remain: the reference point for 'next' (today?) and the return type (ISO string vs. date object) are unspecified, and with no output schema the description should have closed those.

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 coverage is 100% and the schema lists the three accepted strings, but the description adds meaning the schema lacks: the mapping of each risk value to its concrete review interval in days. That is genuine value beyond the structured field.

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?

Specific verb and resource: 'Return the next review date for a risk level,' with the scope narrowed by the risk input. It is plainly distinct from siblings like assess_workplace and list_hazards, though it never names them or explicitly contrasts itself.

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?

Usage is only implied: an agent can infer this is a lookup used to schedule the next review, but there is no statement of when to call it versus assess_workplace, documentation, or list_hazards, and no preconditions or exclusions.

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