Föräldraledighetsplanen

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, and closed-world behavior. The description adds useful context that it follows FK 2026 rules and returns a source and planner link, but it does not describe calculation caps, assumptions, or the exact response shape beyond the two amounts.

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 and front-loads the calculation, output units, and regulatory basis. Every sentence earns its place with no redundant restatement of the tool name.

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?

This is a low-complexity calculation tool with two fully documented parameters and annotations covering safety behavior. The description supplies the key return values (SEK/day, SEK/month gross) and source/link, though without an output schema it could say slightly more about the exact returned structure.

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 both parameters are already documented in the schema. The description only restates the monthly salary concept and adds no extra meaning for manadslon or dagar_per_vecka, matching the baseline 3 for high schema coverage.

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: calculating parental benefit in SEK/day and SEK/month gross for a monthly salary under Försäkringskassan 2026 rules. It is clear what the tool does, though it does not explicitly contrast itself with siblings such as plan_leave or get_rules_2026.

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?

There is no explicit guidance on when to use this tool versus explain_rule, get_rules_2026, or plan_leave. Usage is only implied by the calculation wording, leaving the agent to infer the appropriate routing.

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, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds one genuinely useful behavioral fact beyond that: answers come with a source from Försäkringskassan. It still does not say whether the response is free text, how long it is, or what happens for out-of-scope questions.

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 no filler; the verb and resource come first and the parenthetical is a compact scope specifier. The dense enumeration makes it slightly hard to parse but every element carries routing 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?

For a one-parameter, read-only tool with no output schema, the description is adequate on scope but silent on return shape (beyond 'with source') and on the closest sibling get_rules_2026, which is the most likely source of mis-selection. Complete enough to call, not complete enough to route confidently.

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?

With one parameter at 0% schema coverage, the description must compensate. The parenthetical topic list effectively bounds what 'fraga' may concern, which is real added value, but the parameter itself is never named or characterized (question text? keywords? language?), leaving the agent to guess the expected input form.

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 gives a specific verb ('Förklara') and a specific resource ('en regel om föräldrapenning/föräldraledighet 2026') and even enumerates the covered subtopics (dagar, tak, dubbeldagar, spara dagar, grundnivå, skatt, VAB). An agent can tell what it does, but nothing distinguishes it from the sibling get_rules_2026, which appears to address the same knowledge domain.

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: the enumerated topic list suggests 'use this when the question concerns one of these areas'. There is no explicit statement of when to prefer this over get_rules_2026 or calc_benefit, and no prerequisites or exclusions are given, so the agent must infer routing.

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 establish the safe, idempotent, closed-world read profile, so the bar is lower. The description adds genuine value beyond them by disclosing provenance ('med källor från Försäkringskassan') and the fact that the return set is exhaustive ('alla'), which tells the agent no pagination or filtering is needed.

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: verb, scope, year, enumerated contents, then provenance. No filler, no repetition of the tool name, and the parenthetical list is compact.

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?

There is no output schema, and the description compensates by enumerating exactly which rule values come back plus their authoritative source. Paired with annotations that cover the safety profile and a zero-parameter schema, an agent has everything needed to call this correctly.

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 the baseline is 4 and the description correctly gives no parameter guidance. The enumerated field list describes what the (implicit) response contains rather than any input, which is appropriate here.

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 ('Hämta') and a precisely scoped resource ('alla regelvärden för föräldrapenning 2026') and enumerates the returned fields (dagar, tak, grund- och lägstanivå, prisbasbelopp, formel). This makes it clearly the raw-data lookup versus the sibling tools calc_benefit, explain_rule and plan_leave, though no sibling is named explicitly.

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 phrasing 'alla regelvärden' implies this is the source-of-truth fetch that should precede calc_benefit or explain_rule, but the description never states when to use it instead of those siblings or any ordering/prerequisite. Usage is inferred rather than guided.

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 readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds that it returns 'källa och länk till planeraren', which is useful since no output schema exists, but it says nothing about input constraints (e.g. what happens if more than 2 parents are supplied, or how the 480-day cap interacts with onskemal).

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 tight sentence with the core purpose front-loaded and the return information second. No wasted words, though brevity comes at the cost of the parameter detail noted above.

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 read-only calculation with no output schema, disclosing source and planner link is reasonable, and 'datum och belopp per månad' sketches the return shape. However, with nested objects and documented-coverage gaps on two of three parameters, an agent still lacks enough detail to construct a correct call.

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 only 33%: 'onskemal.dagar_per_vecka' and the entire 'foraldrar' array (manadslon, namn) are undocumented. The description only loosely gestures at these ('1–2 föräldrar', 'belopp per månad') and never explains days_per_week, the 0–1 share semantics, or salary units, so it does not compensate for the coverage gap.

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 ('Föreslå en fördelning') plus resource (480 föräldradagar) and concrete output detail (datum och belopp per månad). It's clear what the tool does, but it never mentions how it differs from calc_benefit or explain_rule.

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 domain (planning a parental-leave split between 1–2 parents), but there is no explicit when-to-use guidance and no reference to the sibling tools calc_benefit or explain_rule that an agent could confuse it with.

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