JogsiMérleg

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

With no annotations, the description carries the full behavioral burden. It only restates the count constraint already present in the schema, without disclosing read-only behavior, error handling, ordering, or what the comparison returns.

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 a single front-loaded sentence with zero wasted words. It efficiently conveys the core operation and scope.

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 simple one-parameter tool this is minimally viable, but with no annotations and no output schema, the description leaves gaps around usage routing, return format, and behavioral details. It is adequate but not fully complete.

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 0% for the single 'ids' parameter. The description adds that the ids refer to driving schools and that 2–5 are compared, but it does not clarify id format, source, or any further constraints beyond the schema's min/max.

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 ('Side-by-side comparison'), resource ('driving schools'), and scope ('2–5 by id'). It clearly distinguishes this from siblings like get_school (single school) and search_schools (search rather than direct comparison).

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 nature of a comparison tool, but the description does not explicitly say when to use this versus get_school or search_schools, nor does it name any prerequisites or exclusions.

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 provided, so the description carries the full burden. It does not state whether this is read-only (though 'Full official data for one school' implies read), what happens if the id doesn't exist, or whether KAV ids are the only accepted format. For a tool with zero structured behavioral hints, this is a notable gap.

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 dense sentence that front-loads the purpose and then enumerates the returned fields. No filler, though the parenthetical Hungarian gloss is an aside rather than essential.

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?

The return-value enumeration compensates for the absence of an output schema, and the KAV id hint compensates for the undocumented parameter. But with no annotations and no schema descriptions, an agent still doesn't know error behavior, auth requirements, or id format. Minimum viable.

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 0% and the single 'id' parameter is undocumented in the schema. The description only partially compensates by naming KAV id and its Hungarian expansion (képzőszervi azonosító), but does not specify format (numeric? string?), whether it must be exact, or what happens on invalid ids. With 1 required parameter and zero coverage, more is needed.

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+resource: retrieves full official data for one driving school. The enumerated fields (address, categories, VSM/ÁKÓ stats, ranks) concretely define the return. It doesn't explicitly contrast with siblings like search_schools, but the 'one school by KAV id' framing implies lookup-by-id versus search.

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?

Implied usage: look up a single known school by its identifier. No explicit when-to-use / when-not guidance and no named alternative (e.g., 'use search_schools when you don't have an id'). Adequate but leaves the agent to infer selection.

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 behavioral burden, yet it only describes the payload. It does not explain that min_count filters the results, whether the list is paginated or complete, or how the average pass rate is aggregated.

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 no filler, and the key scoping information (Hungarian towns with driving schools) is front-loaded. It reads as a label fragment rather than a complete sentence, but nothing is wasted.

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 no annotations, no output schema, and an undocumented parameter, the description should do more. It hints at the return fields but leaves the parameter behavior and any filtering or ordering semantics undefined.

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 single parameter min_count has 0% schema description coverage, so the description is the only place it could be explained. Instead the description never references it, leaving the agent to guess that it likely thresholds towns by number of driving schools.

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 the resource (Hungarian towns with driving schools) and the data it surfaces (school counts, average practical exam pass rate), so an agent can tell this is a city-level listing tool rather than a school-level one like get_school or search_schools. It lacks an explicit verb such as 'list' and never directly contrasts itself with its siblings, so it stops short of 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?

There is no when-to-use guidance, no stated prerequisites, and no mention of the four sibling tools (compare_schools, get_school, request_offers, search_schools). The agent must infer usage purely from the topical content.

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 discloses the key behavioral facts: this is an outbound side effect that causes third parties (driving schools) to contact the user, and that the user's name and contact details are transmitted to them. It omits secondary traits such as reversibility, failure behavior, or what the call returns, which keeps it short of a 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?

Two sentences, zero filler, and the consent constraint is front-loaded immediately after the purpose statement. Every clause carries actionable 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 PII-sharing mutation with no annotations and no output schema, the description covers the critical consent gate and the consequence of sharing contact details. It stops short of explaining what happens after submission (success/failure, whether schools' offers return via this tool) or the meaning of the message/category parameters, which is the remaining 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 only 17% across 6 parameters, so the description must compensate. It does add real meaning for userConsent (the consent flag must be true only when the user has agreed) and restates the 1–3 bound on schoolIds that the schema enforces via min/maxItems, but message, category, name and contact are left entirely to 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 (send), resource (the user's enquiry), recipients (1–3 driving schools) and the resulting action (schools contact the user with an offer). This is clearly a mutating outreach tool, making it trivially distinguishable from the read-oriented siblings get_school, search_schools, compare_schools and list_cities.

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 an explicit gating condition: 'ONLY call this when the user has explicitly asked for it and agreed that their name and contact details are shared with the selected schools', and ties it to setting userConsent=true. It states both when to call and the precondition that must hold, leaving nothing 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?

With no annotations supplied, the description carries full burden. It does disclose valuable behavioral context — results are ranked, the index scale is 0-10 with 5 as the national average, and scores derive from KAV exam pass rates (VSM) and lesson hours (ÁKÓ). It does not disclose return shape, pagination, how missing filters are handled, or the effect of the default limit.

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 dense sentence that front-loads the resource and the ranking semantics, then lists filters. Every clause carries information, though packing scoring methodology and filters into one sentence makes it slightly hard to scan.

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 6-parameter, zero-required search tool with no annotations and no output schema, the description covers the ranking domain and filters well but leaves gaps: no mention of how results are returned, whether an empty result set is possible, sorting beyond the index, or the default/limit behavior.

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%, so the description must compensate, and it does: it explains the score scale and meaning behind min_score, gives example values for city and district, and enumerates valid category codes (B, A, AM, C) that the schema itself leaves as an unconstrained default string. The limit parameter remains unexplained.

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 (search) and resource (Hungarian driving schools) plus the ranking basis (JogsiMérleg index). It is clearly a discovery/ranking tool, implicitly distinct from get_school (single lookup) and compare_schools, but it never explicitly names those siblings to reinforce the distinction.

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?

Provides the filterable dimensions (city, district, category, min_score) with example values, which implies when to use it. However, there is no explicit guidance on when to prefer compare_schools or get_school over this search, nor any prerequisite or exclusion noted.

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