Travel Per Diem & Allowance Calculator

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

With no annotations, the description carries the full burden and largely meets it: it discloses the output shape (one line per allowance/deduction/night plus totals) and notable behavioral exceptions such as 'The three-month rule is not applied' and 'no lodging lines' for employer-paid lodging. It never states that this is a side-effect-free calculation with nothing persisted, which would have been useful for a tool with no annotations, so it falls short of 5.

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 front-loaded with what the tool does and returns before diving into bulleted regime detail, and each bullet is on-topic. It is long and dives deep into statutory rule minutiae that arguably belongs in documentation, which keeps it from a 5.

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 tool with 7 parameters and three rule regimes, the description supplies enough regime-level detail to interpret results, and an output schema exists so return values need not be re-explained. It does not cover error behavior or regime-selection guidance, leaving a small gap.

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 every parameter, and the baseline of 3 applies. The description reinforces the semantics of regime-dependent inputs (meal deductions, Übernachtungspauschale, transport-dependent BMF rules) but adds little syntax or format information beyond what the schema's own field descriptions provide.

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 ('Applies the regime's rules to an itinerary and returns one line per allowance, deduction and night, each with the rule it applied, plus totals'), making the computation nature crystal clear. It nonetheless never names or contrasts itself against the sibling tools (get_per_diem_rates, list_per_diem_regimes, search_per_diem_locations), so a 4 rather than a 5.

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 implied by the granular per-regime rule breakdowns, which tell the agent what to expect when regime is de-bmf, us-gsa or uk-hmrc. There is no explicit statement of when to choose this tool over the lookup siblings, nor any preconditions or exclusions, so it stays at 'implied usage'.

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 burden, and it does disclose meaningful behavior: fallbacks are applied, a source citation and data freshness are included, and the us-gsa fiscal-year selection rule is spelled out (FY2026 vs FY2027 windows). It stops short of stating permission requirements, rate limits, or error behavior.

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 dense sentences, front-loaded with the core purpose and return payload, with the regime-specific rule trailing. Slightly packed but no filler; every clause adds information an agent would otherwise have to guess.

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?

An output schema exists, so the description does not need to explain returns, yet it complements them with freshness, citation, and fallback behavior. The one remaining gap is how the optional locator parameters (city vs. state vs. postal_code) interact, which is left entirely to the schema.

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%, so the baseline is 3, but the description adds real semantics beyond the schema: the us-gsa date-to-fiscal-year mapping (FY2026: 2025-10-01..2026-09-30) is not derivable from the fields, and the fallback note clarifies how an unlisted city resolves.

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 and resource ('returns the lodging and meal allowance') and pins the scope to 'one location under one regime', which cleanly separates it from search_per_diem_locations and calculate_trip_allowance. It goes further to enumerate what comes back (regime breakdowns, fallbacks, citation, freshness), so an agent knows exactly what this call yields.

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 'one location under one regime' scoping implies the lookup use case, but there is no explicit when-to-use/when-not guidance and none of the sibling tools are named as alternatives. An agent must infer that this is the single-point lookup rather than the search or trip-total tool.

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 disclosure burden, and it does add real behavioral context: the listing includes planned-but-not-yet-available regimes, which would surprise an agent expecting only active data. It stops short of stating read-only nature, auth needs, or that no filtering/pagination applies.

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?

A single front-loaded sentence with the verb and resource first, then the useful contents. No filler and nothing repeated from structured fields.

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?

With an output schema present and zero parameters, the description only needs to frame what the list contains, which it does. Ordering, scope, and relationship to the rate/trip tools are left unstated, a minor gap given the low complexity.

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 no parameters, so there is nothing to document; baseline is 4. The description correctly does not waste space explaining inputs.

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 and resource ('Lists the available regimes') and enumerates the payload contents (validity periods, snapshot dates, sources, calculator rules, planned regimes). It does not name a sibling or explain how it differs from get_per_diem_rates, but the resource focus on 'regimes' is distinct enough to identify.

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 this is the discovery/overview call for regimes but gives no explicit when-to-use statement, no prerequisites, and never mentions the alternatives (get_per_diem_rates, search_per_diem_locations, calculate_trip_allowance). Usage must be inferred from the resource name alone.

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 disclosure burden. It does disclose that us-gsa is limited to current fiscal-year destinations and that results feed other tools, which is real behavioral context. However it is silent on pagination behavior (limit/offset), result ordering, and whether results are cached or rate-limited.

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, front-loaded with the purpose and followed by the practical chaining tip; nothing is padded. The only friction is the '/' path notation, which slightly obscures the referenced tools.

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?

With an output schema present, the description needn't explain return values, and full param coverage is handled by the schema. It covers purpose and chaining adequately, but leaves pagination semantics and result ordering unaddressed — minor gaps for a filtered list tool with six parameters.

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 all six parameters are already documented in the schema, establishing the baseline of 3. The description restates the filter dimensions (text, country, state) and adds the us-gsa fiscal-year nuance, but contributes no syntax or format detail 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?

The description names a specific verb and resource ('Lists the locations with their own rate in a regime') and scopes it to text/country/state filtering, which is more precise than the bare title. It does not however explicitly distinguish itself from siblings like get_per_diem_rates or list_per_diem_regimes beyond a parenthetical regime note.

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?

It offers downstream guidance ('Use the returned country/city/state values in /rates and /trip'), which is useful chaining advice. But the referenced tools are written as paths ('/rates', '/trip') rather than by name, so the agent must infer which siblings they map to, and there is no statement of when NOT to use this tool versus get_per_diem_rates.

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