Dojazdomat

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

With no annotations, the description carries the full disclosure burden and does it well: it names the underlying model (Dojazdomat), the averaging window (weekday 7-9 morning), the return contents (nearest stops at both ends), and the unreachable edge case where minutes is null beyond ~2 h. Only minor gaps remain (no auth or rate-limit notes), which is acceptable for a public data lookup.

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 key clause (door-to-door minutes by public transport plus walking) is front-loaded, and edge-case behavior is stated last. The bilingual parenthetical restates the same point, which is mild redundancy but serves a legitimate localization purpose.

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 four-coordinate lookup, the description covers mode, model, averaging window, return contents, and the null/unreachable case. With an output schema present it need not explain return structure further, and the only omission is guidance on sibling selection.

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%, and every parameter is documented with type, unit, WGS84 ranges, and the geographic bounding box. The description adds no syntax or format detail beyond the schema, so the baseline of 3 applies.

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 metric (door-to-door minutes), the mode (public transport plus walking), and the temporal scope (weekday 7-9 average), and it also discloses that nearest stops are returned. It is clear what the tool produces but does not explicitly contrast itself with siblings like rank_neighborhoods or find_place.

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 statement of when to use this tool versus alternatives, nor any prerequisite or exclusion guidance. An agent can infer it is a point-to-point commute query, but nothing routes it away from sibling tools such as rank_neighborhoods.

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 behavioral burden, but this is a zero-parameter, read-only info lookup, so the risk surface is small. It discloses what the response contains (dates, sources, counts, notes, caveats) but says nothing about freshness guarantees, provenance of the portal counts, or that it is a safe read.

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 that moves directly into the content inventory with no preamble. The parenthetical Polish translation adds a small amount of redundancy/noise but the whole definition is still tight.

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 return values need not be expanded further, and the schema description coverage is 100%. For a trivially simple zero-parameter tool, the content inventory is sufficient; only the missing when-to-use framing leaves a 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?

The tool takes zero parameters, so there is no parameter semantics to explain; the baseline for a no-param tool is 4. Nothing in the description is needed to clarify arguments, and nothing misleading is offered.

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 enumerates the specific content the tool delivers (data dates, sources, per-portal listing counts, method notes and caveats), which is more informative than the bare name 'dataset_info'. It does not explicitly contrast itself with siblings, but the siblings (commute_time, find_place, rank_neighborhoods, rent_stats) are functionally unrelated, so no differentiation is needed.

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 trigger condition, and no mention of alternatives. The agent must infer that this is a metadata/reference lookup, likely before or alongside the analytical sibling tools, from the content listing 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 exist, so the description carries the full burden, but it does disclose the return shape (lat/lon pairs) and that lookup is by name. It omits matching semantics (exact vs. substring), not-found behavior, and result ordering, and the output schema is left to explain result structure.

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 short sentences, front-loaded with the core action and followed by the downstream-usage hint; nothing is wasted. The inline Polish translation adds length but serves the tool's bilingual naming convention.

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 two-parameter lookup with an output schema, the description covers purpose, input basis, and downstream usage adequately. Only the 'limit' parameter and no-match behavior remain unexplained, which are minor gaps at this 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?

Schema description coverage is only 50%: the 'query' fragment semantics live in the schema, while 'limit' (default 10, max 25) is undocumented in both the schema and the description. The description adds only 'by name' on top of what the schema already says, so it neither compensates for the gap nor earns more than the baseline.

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 ('find transit stop groups and neighborhoods by name') plus the return value ('lat/lon'), which clearly distinguishes it from the sibling tools that consume coordinates. It stops short of naming any sibling explicitly, so it is clear but not maximally differentiated.

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 second sentence gives real routing guidance: use the resulting coordinates as input for the other tools, which positions find_place as the upstream geocoding step relative to commute_time, rank_neighborhoods, and rent_stats. It does not state any when-not conditions or failure behavior, but the context is unambiguous.

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 behavioral burden and does a good job: it discloses that neighborhoods with fewer than 20 ads are skipped, explains the default sort, and defines the value and Pareto metrics. It is still somewhat vague about the upstream data and rule source by saying 'same data and rules as the map'.

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 the purpose and then supplies the key rules and metrics. It is somewhat dense and includes parenthetical Polish aliases that add clutter, but the content generally earns its place.

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 moderate complexity, high schema coverage, and an output schema, the description is mostly complete. It covers the exclusion rule and default ordering, though it could better explain how this tool relates to the narrower sibling tools.

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 88%, so the schema already documents nearly all parameters. The description reinforces the default sort behavior but adds little parameter-level meaning 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 clearly states a specific verb and resource: ranking Warsaw neighborhoods for a workplace. It distinguishes the result set through its combined rent/commute/value/Pareto criteria, but it does not explicitly contrast the tool with siblings such as rent_stats or commute_time.

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 is implied by 'for a workplace' and the ranking context, but there is no explicit guidance on when to choose this tool over rent_stats or commute_time. It also does not state exclusions beyond the 20-ad threshold.

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 present the description carries the full burden, and it discloses two real behavioral traits: the tool is aggregate-only (no per-ad data) and the k-anonymity-style suppression below 5 matching ads. It does not discuss permissions, rate limits, or freshness of the underlying ad data, 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, efficiently front-loaded with what is computed before the suppression caveat. The only slack is the parenthetical Polish gloss of the same phrase, which duplicates meaning rather than adding it.

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?

Output schema exists, so return values need not be explained, and the schema fully documents all 7 parameters. The description supplies what the schema cannot: the aggregate-only nature, the minimum-sample suppression behavior, and the remediation path. Nothing an agent needs to call this correctly is missing.

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 including radius_m, measure, rooms and area bounds is already documented in the schema. The description references radius_m and 'filters' generally but adds no format, default, or syntactic detail beyond what the schema provides; the baseline of 3 applies.

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 (aggregates) and resource (asking-rent statistics of rental ads) and enumerates the exact output measures (n, median, p25, p75). The spatial scope ('within radius_m of a point') makes the operation unambiguous, and no sibling tool in the set computes rent statistics, so no differentiation is required.

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?

'Aggregates only' tells the agent this returns summary statistics rather than individual listings, and the suppression rule gives an explicit when-not case ('if fewer than 5 ads match, the result is suppressed') plus remediation ('widen radius or relax filters'). It does not name a competing sibling, but none exists in this tool set, so the gap is minor.

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