Schiphol Herrie

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

Beyond the annotations, it discloses that reports are anonymous and public in aggregate, that they feed map badges and daily/weekly rankings, that the loudest aircraft is reported if no identifier is provided, and the per-directory reporting limit. This gives the agent useful behavioral expectations beyond what annotations supply.

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 slightly long but every sentence carries needed information: the action, the public/aggregate behavior, identifier requirements/fallback, rate limiting, and the official-complaint redirect. It is front-loaded with the core action and then layers essential details, but a few phrases like 'as a visitor does from the flight card' are illustrative rather than strictly necessary.

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 six parameters, no output schema, and meaningful side effects, the description covers the important constraints: required lat/lon, optional identifiers, fallback behavior, anonymity, and rate limits. It does not describe what the API returns, which is less critical for a report action because the side effect is clear; this is a minor 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?

With 100% schema coverage, the baseline is 3, but the description goes further by explaining the fallback: if hex/callsign are omitted, the loudest aircraft over the location is reported. It also points the agent to wat_vliegt_over as the source for the hex, adding 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 states a specific action ('report an aircraft as noisy') and the context (visitor action from the flight card on the live map). It is clearly distinct from the sibling tools, which query aircraft ('wat_vliegt_over') and retrieve top reports ('top_meldingen').

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 says to use the hex from wat_vliegt_over or a callsign, names the official complaint alternative (BAS) and where to find it, and gives the deduplication constraint. This is explicit when-to-use and when-not-to-use guidance.

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 value by disclosing that results aggregate data from both visitor reports and the endpoint itself, which is useful behavioral context. 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?

A single, tightly packed sentence that front-loads the core function and the time window before adding data-provenance detail. No wasted words, and the key information appears first.

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 zero-parameter, read-only aggregation tool, the description is nearly complete: it states the resource, time scope, and output contents. It does not describe the exact return format, but no output schema exists and the data nature (flights, airlines, counts) is adequately conveyed.

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, so the baseline is 4. The description goes further by explaining what the returned data contains (flights, airlines, total report counts) and its time scope, adding semantic meaning to the tool's output even though there is no input schema to enrich.

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-resource pair: it reports the most-reported flights and airlines of today and the last 7 days, including total counts. This distinguishes it sharply from siblings meld_herrie (submitting a noise report) and wat_vliegt_over (live aircraft info).

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 explains where the report data comes from (schipholherrie.nl visitors and this endpoint), giving useful context about data provenance. However, it does not explicitly say when to prefer this tool over its siblings or state any exclusions, though the distinct purpose makes the choice fairly obvious.

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 mark the tool as read-only, idempotent, and non-destructive. The description adds valuable behavioral context: the sound level is a modelled estimate, not a measurement, and may differ by 5-10 dB. It also discloses the loudest-first ordering. No contradiction with annotations exists.

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 and front-loaded: it states the core behavior first, then the key uncertainty caveat, then the use cases. Every sentence earns its place and there is no filler.

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 read-only geospatial tool, the description plus schema and annotations cover the essential invocation needs: location, optional threshold, output ordering, unit, and the purpose of finding a hex. Without an output schema, it could mention result limits or data freshness, but these are minor gaps.

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 input schema already describes all parameters with 100% coverage, including lat/lon being WGS84 within the Netherlands and min_db defaulting to 45. The description does not add further parameter-level meaning, so the baseline of 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: it lists aircraft currently over or near a location in the Netherlands, ordered loudest first, with a modelled dB(A) level. It also names concrete use cases, which clearly differentiates it from the sibling tools meld_herrie and top_meldingen.

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 explicitly says to use it to find the hex of an aircraft to report with meld_herrie, or to answer 'what is that plane?'. This gives clear invocation context and points to a sibling, though it does not explicitly mention when to prefer top_meldingen or when not to use this tool.

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