env_noise_limits_check

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

The description discloses that the calculation is purely local ('Rein lokale Berechnung, kein Netzwerk'), which aligns with the readOnlyHint and idempotentHint. It also notes the refusal for military periods and the footnote-driven deviation for ES II first night hour, adding behavioral context beyond what annotations provide. No contradictions with annotations exist.

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?

The description is well-structured with a clear opening sentence, legal basis, use case, and important notes sections. While it is relatively long, each part adds necessary context for a domain-specific legal comparison tool. The structure aids quick scanning and comprehension, though some redundancy exists between the description and 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?

Given the tool's complexity (nested input, four parameters, output schema), the description covers purpose, legal framework, usage context, key exceptions, and return format. It references the expected input source (sibling tool) and addresses edge cases. The presence of an output schema reduces the need to detail return structure in the description, so completeness is satisfactory.

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 input schema already provides detailed descriptions for all parameters, including enum values for period and explanations for sensitivity_level. The description adds marginal value by linking level_db to the sibling tool env_noise_aircraft_at and reiterating legal context, but the schema coverage is high enough that the description does not significantly shift understanding of parameter semantics.

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 clearly states 'Vergleicht einen Fluglärm-Beurteilungspegel gegen die LSV-Belastungsgrenzwerte' (compares a flight noise assessment level against LSV limit values), specifying a concrete verb and resource. It also cites the exact legal basis (LSV, Anhang 5) and differentiates the tool from siblings like env_noise_aircraft_at by focusing on legal classification rather than noise level retrieval.

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 use case section explicitly tells when to use this tool: 'Einen dB-Wert aus env_noise_aircraft_at (oder aus einem Gutachten) rechtlich einordnen'. The important notes explain that the tool deliberately refuses the 'military' period because Annex 5 only applies to civil airports, providing a clear exclusion criterion. It also highlights the special case for ES II in the first night hour, guiding correct parameter choice.

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