openaq-mcp-server

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

Annotations already indicate readOnlyHint=true, so the read-only nature is covered. The description adds detail about the return content (each measurement table with row count and column names) and the DataCanvas requirement, providing context beyond the annotation without contradicting it.

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 with zero waste. The primary action is front-loaded ('List the tables and columns'), followed by purpose, return specifics, and a prerequisite. Every sentence contributes necessary 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?

Given the presence of an output schema (as indicated by the context signal), the description need not detail return types. It already explains what the tool returns (tables, row counts, column names) and the prerequisite. An agent receives enough to call it correctly without missing context.

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% and the canvas_id parameter has a clear, specific description ('DataCanvas id returned by openaq_get_measurements when a series spilled'). The tool description itself does not add parameter details, but the schema fully documents the parameter, 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 clearly states the verb (list), the resource (tables and columns on a DataCanvas), and the intended purpose (writing valid SQL for openaq_dataframe_query). It distinguishes itself from sibling query tools by focusing on schema discovery rather than data retrieval.

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?

Explicitly explains when to use: 'so you can write valid SQL for openaq_dataframe_query without guessing column names.' It also names the prerequisite ('Requires DataCanvas to be enabled') and implicitly positions it as a setup step before querying. No ambiguity about its role in the workflow.

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 declare readOnlyHint=true, and the description reinforces this with 'read-only SQL SELECT' and adds specifics about rejected operations ('writes, DDL, and file/network table functions'). This expands beyond the annotation, clarifying constraints and expectations.

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 (three sentences), front-loads the main action ('Run a read-only SQL SELECT'), and efficiently covers table references, typical use cases, and restrictions without redundancy.

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 full schema parameter coverage, the description supplies all essential context: allowed SQL subset, how to reference tables, and when to use the tool. No critical information is missing for correct invocation.

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 both parameters (sql, canvas_id) already have detailed descriptions in the schema, including table naming and the recommendation to use describe first. The tool description reiterates this but does not add novel 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 states a specific verb ('Run a read-only SQL SELECT') and resource ('measurement tables staged on a DataCanvas'), and distinguishes itself from siblings by focusing on querying staged measurement data. It clearly differentiates from retrieval tools like openaq_get_measurements and openaq_dataframe_describe.

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 provides explicit usage context: for aggregation (monthly means, exceedance counts) and cross-sensor comparison over large series. It also recommends running openaq_dataframe_describe first to inspect table/column names. It doesn't explicitly state when not to use it, but the purpose makes that inferable.

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, openWorldHint, and idempotentHint, so the safety profile is covered. The description adds valuable context beyond that: coverage is uneven and real, absence of stations means no monitoring, not clean air, and distance is only returned for coordinate searches. This enriches the agent's mental model of result interpretation, though it does not disclose pagination quirks (which live in the schema).

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 concise but information-dense, with three clear sentences: purpose and selection criteria, return fields, then usage and caveats. It is front-loaded with the central action, and every sentence earns its place by adding distinct value (purpose, returns, sequence, limitation, alternative). No filler or redundancy.

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 tool has 7 optional parameters, a rich output schema, and clear annotations, the description covers all the essential contextual pieces: what the tool returns (key fields), how it relates to sibling tools (first step), its data-source limitations, and the recommended alternative for modeled data. Nothing an agent needs to choose and invoke it 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?

The input schema has 100% description coverage, with each parameter explained in detail (e.g., coordinates pattern, bbox format, radius bounds, page/limit behavior). The description adds only marginal parameter-level detail, such as implying bbox vs coordinates via 'within a bounding box' and noting distance only when searching by coordinates. Since the schema already carries the full burden, a 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 ('Find') and a precise resource ('air-quality monitoring stations') with explicit selection criteria: near a point, within a bounding box, or by country. It also distinguishes itself from the modeled-data alternative by explicitly noting it uses physical sensors, and from sibling openaq tools by positioning itself as the required first step for readings/measurements. This leaves no ambiguity about what the tool does.

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 explicit when-to-use guidance: it is the first step for openaq_get_readings and openaq_get_measurements, and it names the open-meteo alternative for dense modeled coverage. It also implicitly excludes modeled data by stating it is physical sensors only. This clearly routes the agent to the correct tool for each scenario.

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 carry readOnlyHint/openWorldHint/idempotentHint, lowering the burden. The description adds genuinely valuable non-obvious behavior beyond that: the DataCanvas spill mechanism (preview + canvasId + table name), internal paging up to a spill threshold, and the explicit unit non-conversion ('the server never converts between µg/m³, ppm, and ppb'). These give the agent actionable expectations not visible in annotations. It doesn't specify the exact spill threshold, a minor 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?

Single dense paragraph, front-loaded with purpose before mechanics. Every sentence earns its place: use case, spill behavior, unit handling, and aggregation tradeoffs. Slightly run-on with semicolon/colon chains, but efficient overall and avoids redundancy with the schema.

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 7-parameter tool with an output schema, the description is strong: it covers the spill path (critical for large ranges), unit semantics, aggregation choice tradeoffs, and references openaq_find_locations/openaq_dataframe_query for id sourcing and follow-up. Since an output schema exists, return values need no explanation. Minor omissions are the exact spill threshold and explicit differentiation from get_readings.

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 thoroughly (datetime formats, defaults, limits, source of ids). The description adds some value — the per-bucket statistical summary composition (min, median, max, mean, sd) for hourly/daily aggregation, and the conceptual pairing of locationId+parametersId — but these are marginal additions over an already-rich 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 verb and resource — 'Historical measurement series for one pollutant at one station over a date range' — and immediately gives the intended use cases ('trend analysis', 'was last week worse than the monthly average?'). The single-pollutant, single-station scope distinguishes it from broader siblings like get_readings, and the DataCanvas spill explicitly ties it to openaq_dataframe_query.

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 clear selection context: 'work in stations', trend-focused use, and concrete aggregation guidance ('Use "daily" for multi-month trends... "raw" for fine-grained recent analysis'). It also names openaq_dataframe_query as the follow-up when results spill. However, it never explicitly says when NOT to use this tool versus the sibling openaq_get_readings, so the routing guidance stops short of full 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?

Annotations already declare readOnlyHint, openWorldHint, and idempotentHint, so the safety profile is covered. The description adds substantial behavioral context: the output structure (one record per parameter with value, unit, UTC/local timestamps, sensor id), the join that the raw feed lacks, the recency caveat tied to station cadence, and the warning that these are measured observations with gaps—not a modeled grid. This goes well beyond what annotations provide and sets accurate expectations.

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 dense but each sentence earns its place: it states the core purpose, details the returned record structure, gives both invocation routes, and flags the recency and data-coverage caveats. It is a bit longer than minimal but everything included is relevant. The structure front-loads the purpose and then expands logically. A slightly tighter wording could trim a few words, but no sentence is redundant.

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 tool with three optional parameters, two distinct call patterns, and an output schema already present, the description covers all the essential aspects an agent needs: how the result is shaped, how to select the target station, the dependency between parameters, and the reliability caveat about timestamps. The output schema covers the exact return fields, so the description does not need to repeat them. Nothing critical 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?

The input schema already gives detailed descriptions for all three parameters (100% coverage). The description adds value by explaining the relationship and constraints: locationId OR coordinates, coordinates as a 'fallback' that auto-resolves within 25km, and parametersId being 'Required with coordinates' while optionally filtering when locationId is used. This conditional logic is not obvious from the schema alone and meaningfully helps an agent invoke the tool correctly.

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 starts with a precise verb and resource: 'Latest measured value for every sensor at a monitoring station'. It also brands itself as 'the current-conditions tool', which cleanly separates it from siblings like openaq_get_measurements (historical data). The scope (per-sensor, latest value) and the join detail (carries pollutant and unit) leave no ambiguity about what the tool returns.

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 clearly explains the two entry modes (locationId or coordinates) and the condition that coordinates requires parametersId. It even names the source for locationId (openaq_find_locations). It stops short of explicitly stating 'use this for current conditions, use openaq_get_measurements for historical trends', but the 'current-conditions tool' label and the mention of recency implicitly frame the appropriate use case.

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 and idempotentHint=true, so the safety profile is covered. The description adds context that coverage is uneven worldwide, that the catalog is bounded (~153 countries), and that the date span reveals recency of data. This goes beyond what annotations state and helps the agent understand the tool's limitations without contradicting any annotation.

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 compact sentences front-load the core value (country-level coverage) and then the practical use (availability check before find_locations). No filler or redundancy; every sentence 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 tool is read-only, idempotent, has a fully documented 2-parameter schema, and includes an output schema, the description fully covers what the agent needs to decide when and how to call it. It explains the data's meaning, the usage path, and the coverage caveat. Nothing critical 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 coverage is 100% and both parameters are described in detail: query explains case-insensitive exact-vs-substring behavior and the two-letter ISO code rule; parametersId explains filtering by id, gives an example, notes multiple ids per pollutant, and mentions composition with query. The description itself does not add parameter-level semantics beyond what the schema provides, 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 uses a specific verb ('list') with a clear resource ('countries') and states exactly what the catalog contains: id, ISO code, name, date span, and measured parameters. It also frames the purpose as an availability check and a pre-step to openaq_find_locations, making it distinct from siblings like openaq_list_parameters or openaq_find_locations.

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 tells when to use it: before a regional sweep and before calling openaq_find_locations, and gives concrete questions it answers (e.g., 'which countries have NO2 monitoring?', 'whether a country has recent data'). It does not explicitly state when not to use it, but the context is clear and no direct sibling competes for this narrow role, so exclusion is not critical.

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 and idempotentHint, covering safety. The description adds behavioral context: 'A small bounded catalog fetched live from OpenAQ' reveals that the tool performs a live fetch and returns a limited set, which is useful for planning. It also notes the default behavior for pollutantsOnly via the parameter, but that is schema-covered. No contradictions with annotations; the added info is valuable but not extensive.

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 three sentences with zero fluff. It leads with the tool's core function (catalog of pollutants and units), then explains purpose and usage, and ends with a note on the bounded live fetch. Every sentence earns its place, and the critical unit-disambiguation point is front-loaded.

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-list tool with a rich output schema, the description is complete. It covers the tool's output content (fields), the filtering parameters, the use cases, and the bounded nature. It does not need to describe return format because the output schema defines it. There are no obvious gaps an agent would need to know to call it 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?

Schema description coverage is 100%, so the baseline is 3. The description does not add new parameter meanings beyond what the schema already provides: the query parameter's filtering behavior and the pollutantsOnly flag are both fully documented in the schema with examples and defaults. The description reuses the same information without extension, so no extra semantic value is added.

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 the tool lists a catalog of pollutants with canonical units, specifying the exact fields (id, code, display name, unit, description). It distinguishes itself from siblings like openaq_list_countries by focusing on pollutant parameters and unit disambiguation, and it explicitly mentions the sibling tools (openaq_find_locations, openaq_get_readings, openaq_get_measurements) that it supports. Purpose is unambiguous.

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 explicit when-to-use guidance: 'use this to pick the exact parametersId for openaq_find_locations / openaq_get_readings / openaq_get_measurements and to interpret a reading's unit.' It also indicates that omitting the query lists everything, which clarifies a common usage. It does not explicitly state when not to use it or name alternatives to avoid, but the context is strong enough to route an agent correctly.

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