Australia Air Quality Sites (NSW) MCP

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

With no annotations, the description does add useful behavioral constraints: it discloses a subscriber/PRO access requirement, a fixed 50 km radius, and an NSW geographic restriction. It does not disclose return contents, pagination, error behavior, or whether the access_token is mandatory in practice.

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?

It is brief and front-loads the key constraint, but the fragment 'PRO. AQ sites' is not self-explanatory and reads as unexplained jargon rather than efficient communication.

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 no annotations and no output schema, the description is too thin: it omits what 'AQ' means, what results look like, authentication expectations beyond the schema, and any behavioral caveats around the fixed radius or NSW scope.

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 50%: access_token is documented in the schema, but postcode has no description there. The description compensates partially by implying postcode must be an NSW postcode tied to a 50 km radius, but it does not specify format, validation, or what happens for non-NSW postcodes.

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?

It states a specific operation (find sites within 50 km of a postcode), which is distinguishable from the generic siblings sites and site_search. However, the abbreviation 'AQ sites' and the leading 'PRO.' fragment leave the resource ambiguous; an agent cannot be fully sure what 'AQ' refers to without outside knowledge.

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 guidance on when to use this tool over site_search or sites, and no stated exclusions or prerequisites beyond the cryptic 'PRO.' prefix. The agent must infer that proximity-to-postcode is the selecting condition.

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 disclosure burden; it does contribute two real behavioral facts — the call is free and results are truncated to the first 10. It omits whether this is read-only (strongly implied by a site listing), whether the truncation is stable/ordered, and what fields come back.

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?

One short fragment with the cost cue and the truncation limit both front-loaded. Nothing is wasted, and every token carries 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 zero-argument tool this is close to adequate, but with no output schema the description never indicates what a 'site' record contains (id, name, coordinates), which the agent needs to chain into site_search or near_postcode.

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 schema has zero parameters, so baseline is 4; there is nothing parameter-level for the description to explain or omit.

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 resource (NSW air quality monitoring sites) and a concrete scope limit (first 10), so an agent knows exactly what it gets. It stops short of distinguishing itself from siblings like site_search or near_postcode, leaving the 'FREE' prefix as the only differentiation signal.

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?

'FREE' hints that other tools may be metered, which is weak implied guidance. There is no statement of when to choose this over site_search (e.g., unfiltered full list vs. querying) or near_postcode (proximity lookup).

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. It flags 'PRO' (a paid tier) but never says that a subscriber access_token is required for the call to succeed, nor whether results are exact/substring matches, capped, or paginated. The schema's token hint is the only auth signal, and it lives outside the description.

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 clauses with the operation front-loaded; nothing is wasted. The 'PRO.' prefix is terse to the point of ambiguity — it reads as a tier marker but is never expanded, so a small deduction.

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?

No output schema exists, so the description should describe what comes back (site objects? IDs? count?) and what an empty match yields; it says none of that. For a search tool with an undocumented required param and no annotations, this is under-specified.

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 50%: access_token is documented inline but 'keyword' is a bare string in the schema. The description compensates by telling the agent the keyword matches either a site name or a region, which is real added semantics. It still says nothing about matching behavior or partial terms.

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 NSW AQ sites by name/region keyword.' The scope (NSW air-quality sites) and match dimension (name/region) are clear. It does not explicitly distinguish itself from the sibling 'sites' (list all) or 'near_postcode' (spatial search), 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 exclusion, and no reference to the obvious alternatives 'near_postcode' and 'sites'. An agent must infer that keyword lookup is the right path instead of a postcode or full listing.

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