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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the safety profile is covered. The description adds meaningful behavioral context beyond annotations by disclosing the exact BMF PAP methodology, the components included (Lohnsteuer, Solidaritätszuschlag, Kirchensteuer, Sozialabgaben), and the inclusion of selected allowances and state-specific family allowance. No contradiction with annotations.

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 compact: a front-loaded purpose line and one detailed sentence on methodology. Every sentence adds meaningful information, and the structure suits a tool with 29 parameters without becoming bloated.

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 complex calculation tool, the description covers the core purpose, method, tax components, allowances, and special payments, while the output schema handles return-value details and annotations cover safety. The only notable gap is the lack of explicit guidance on when to choose this over calculate_standard_salary.

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%, so the schema already documents all 29 parameters. The description adds only general context about selected Zulagen-IDs and the state-specific Familienzuschlag, but does not enrich individual parameter semantics beyond what the schema provides. Baseline 3 is appropriate.

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 states a specific verb and resource: 'Berechnet das exakte Brutto, Netto und die jährliche Sonderzahlung inklusive ausgewählter Zulagen-IDs und bundeslandspezifischem Familienzuschlag.' It clearly distinguishes itself from the sibling option-retrieval tools and from a standard salary calculator by emphasizing complete ÖD-Berechnung and BMF-PAP-based net calculation.

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 gives a clear context: use for complete German public-service salary calculation with allowances and exact tax/social deductions according to the BMF PAP. However, it does not explicitly contrast this tool with calculate_standard_salary or state when not to use it, leaving some differentiation to inference.

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?

Annotations indicate readOnlyHint=true, idempotentHint=true, and no destructive action. The description adds context about using the BMF's Programmablaufplan and supports precise tax/social insurance calculations, which is useful. However, it does not disclose important behaviors like requiring specific inputs for certain employment types, potential errors for invalid combinations, or that 'sonstige' requires bruttoGehalt, though the schema does indicate that. No contradiction found.

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 two sentences, but it is dense with technical jargon and German acronyms, which may hinder quick comprehension. It front-loads the main purpose but is not as concise as it could be, given the complexity of the tool. It is not overly long, but it could be restructured for clarity.

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 high complexity (27 params, 9 enums, multiple employment types), the description covers the core modes and mentions exact tax/social insurance calculations, but it omits guidance on how parameters interact (e.g., needed fields for each employment type) and potential validation rules. The output schema exists, so return values are presumably covered. The description is reasonably complete but could add more usage context.

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 schema provides 100% coverage for all 27 parameters, with detailed descriptions for each. The description adds minimal param guidance: it clarifies that 'sonstige' uses 'bruttoGehalt' and that the calculation is based on current PAP, but does not explain all parameters. Since coverage is full, the baseline is 3 and the description adds modest value.

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 it calculates base salary, gross, net, and special payments from core data, distinguishing between tariff/Beamte and 'sonstige' modes. However, the German acronyms (DIREKTBERECHNUNG & BRUTTO-NETTO-RECHNER) may be confusing, and the purpose is not explicitly differentiated from sibling tools like calculate_agent_salary.

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 it supports multiple employment types and covers both gross-net calculation and tariff/Beamte modes, but it does not explicitly state when to use this tool over calculate_agent_salary or get_public_sector_options. No exclusion criteria or explicit alternatives are given, so the agent must infer usage from the tool name and siblings.

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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds the scope of what is returned but does not disclose additional behavioral traits such as ordering, caching, or response size. With annotations present, this is adequate but not rich.

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 one focused sentence, front-loaded with the action ('Liefert eine Übersicht') and followed by the precise objects covered. No filler or redundancy.

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 parameterless, read-only options-retrieval tool with an output schema, the description is complete. It tells the agent exactly what domain data is covered, while the output schema covers return structure and annotations cover safety.

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 has zero parameters and 100% schema coverage, so there is nothing for the description to compensate for. According to the baseline for no-parameter tools, a 4 is appropriate.

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 uses a specific verb ('Liefert eine Übersicht') and names the exact resource: all Dienstherren (Bund & 16 Bundesländer), collective agreements (TVöD, TV-L, etc.), and available Besoldungsgruppen. This clearly distinguishes it from the calculator siblings, which focus on salary computation rather than option listing.

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 gives clear context: this tool returns an overview of public-sector employers, tariff agreements, and salary groups. It does not explicitly name exclusions or alternatives, but the content makes its role as an options/metadata lookup self-evident compared to the calculate_* siblings.

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?

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so no safety warnings are needed. The description adds that the result includes all steps with Grundgehalt and all selectable allowances/family allowance rules, which is useful context beyond the annotations, but it does not disclose additional behavioral caveats.

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 concise, front-loaded sentence with a clear 'DISCOVERY:' label and a comprehensive list of returned data. It is appropriately sized, though the long list of result categories could be structured slightly more readably without losing information.

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 output schema, full parameter descriptions, and strong annotations, the description is sufficient for an agent to understand the tool's purpose and inputs. It captures the core return categories and implies the conditional employmentType/dienstherr/tarifvertrag requirements without needing to restate them.

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%, so every parameter is already documented. The description only restates the core inputs (Dienstherr/Tarifvertrag, Gruppe) without adding new syntax, formatting, or conditional-dependency details beyond what the schema provides.

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 uses the verb 'Liefert' and specifies a concrete resource: salary steps with basic salary, selectable position allowances, office allowances, and family allowance rules for a Dienstherr/Tarifvertrag and a group. It clearly indicates a discovery/lookup role rather than a calculation tool, though it does not explicitly differentiate itself from the calculate_* siblings.

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 'DISCOVERY:' prefix and the scope ('für einen Dienstherrn oder Tarifvertrag und eine Gruppe') imply this tool is for retrieving salary-table and allowance options. However, it does not explicitly state when to prefer this tool over calculate_agent_salary or calculate_standard_salary, nor does it give exclusions, so the guidance is implied rather than explicit.

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