Australia CPI (ABS) MCP

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

No annotations are provided, so the description carries the full burden and fails to disclose return shape, auth behavior, or rate limits. 'PRO.' is the only behavioral hint (premium/subscriber gating), and it is never explained.

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 fragments, so nothing is wasted and it is front-loaded, but the terseness crosses into under-specification and unexplained acronyms rather than genuine economy.

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?

Low complexity (one optional auth param, no output schema, no annotations) lowers the bar, but an agent still cannot infer what 'H3 activity' means, what 'Full' vs non-full returns, or how this differs from the several similarly named siblings.

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?

Only one optional parameter and schema coverage is 100%, so the schema fully documents access_token. The description adds nothing beyond that, which meets the baseline for high-coverage schemas.

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?

Names a resource ('H3 activity row') and implies retrieval of the 'latest' one, but 'H3' is undefined jargon and 'Full' is unexplained. With siblings like latest_activity and activity_indicator, nothing in the description lets an agent tell which tool returns what.

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?

No when-to-use, when-not-to-use, or alternative-naming guidance at all. 'PRO.' hints at a subscription tier but does not help an agent choose this tool over latest_activity.

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 must carry the behavioral burden. It discloses the substring-match behavior of the name parameter, which is useful, but says nothing about authentication requirements, whether the tool is premium-gated, the return shape (latest vs. recent values, count of recent values), or error behavior for unknown names.

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 short and front-loaded, but the unexplained 'PRO.' token consumes emphasis without adding meaning, and the sentence compresses away needed detail rather than being efficiently dense.

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, no output schema, an undocumented required parameter, and an auth token parameter, the description is far too thin. An agent cannot confidently call this tool correctly based on the description alone.

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 50%: access_token is documented in the schema, but name is a bare string with no description. The description partially compensates by stating that name is matched as a substring, which is genuine semantic value, but it does not specify matching rules, case sensitivity, or what happens with multiple matches.

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 resource ('indicator') and operation ('latest + recent values'), plus a substring matching behavior on the name. However, 'indicator' is never defined and the 'PRO.' prefix is unexplained, so an agent cannot distinguish this from siblings like activity_full_latest or latest_activity.

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 the numerous sibling 'latest' tools, nor any explanation of what 'PRO' implies (paid tier? auth requirement?). The agent is left to infer selection entirely.

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 it discloses little: only that data starts in 2020 and that access is 'PRO' (implying a subscription). It says nothing about data frequency (monthly? quarterly?), return volume, ordering, or what happens with an invalid token, though the token parameter description hints at auth.

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 fragments, front-loaded with the tier marker and the core resource/scope. Nothing is wasted, though the terseness borders on under-specification rather than disciplined brevity.

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 one-parameter read tool with no output schema, the essentials are nearly covered, but an agent still cannot tell the data granularity, the response shape, or the size of the history returned. Given no annotations and no output schema, the description should have supplied a bit more about the returned series.

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?

There is a single parameter with 100% schema description coverage, so the schema fully documents access_token and the baseline is 3. The description adds a mild signal that the token is a subscriber credential via the 'PRO' label, but nothing beyond what the schema already states.

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 and scope: ABS headline CPI history starting from 2020. An agent can distinguish it from latest_cpi (a snapshot) by the word 'history' plus the start date. It gives no explicit comparison to siblings such as cpi_meta or inflation_group, which keeps it at 4 rather than 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?

The description gives no when-to-use or when-not-to-use guidance and never names an alternative tool. The 'PRO' prefix hints at a premium/paid tier but does not state prerequisites or what to do if the caller lacks access. Only inferred usage is available.

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 it discloses almost nothing: the "PRO" prefix implies a subscription gate but doesn't say what happens without one, and nothing states that this is a read-only operation or what the response looks like. The access_token field in the schema implies auth, but the description itself doesn't address 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 short fragments with no filler, which is good, but the brevity comes at the cost of substance rather than being tight. "PRO." is front-loaded but unexplained, and the second fragment is the only content.

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?

There is no output schema and no annotations, so the description is the only source of information about what this tool returns — yet it never explains which metadata (series list, dimensions, units, frequency) an agent would get back. For a metadata/discovery tool, that omission leaves the agent unable to decide whether calling it is worthwhile.

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?

Only one parameter exists and schema description coverage is 100%, so the access_token semantics are fully documented in the schema. The description adds nothing beyond that, which is the expected baseline when the schema does the work.

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?

"Dataset structure/metadata for the CPI query" identifies the resource domain (CPI metadata) and implies this is the schema/structure companion to the data-returning siblings like cpi_history and latest_cpi. However, there is no verb and no explicit statement of what metadata is exposed, so the agent must infer the purpose from the tool name and sibling set rather than reading it directly.

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?

No guidance on when to call this versus cpi_history, cpi_group, or latest_cpi. The only usage-relevant signal is the leading "PRO", which hints at a paid-tier prerequisite but is never explained. No prerequisites, no exclusions, no alternatives named.

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 says nothing about read-only nature, auth requirements beyond the parameter's own note, rate limits, or what "key/value" output contains. "PRO" hints at a tier restriction, which is the only behavioral signal present.

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 extremely short and front-loaded, but the brevity is under-specification rather than economy — the two fragments convey little and the leading "PRO." is unexplained.

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 must explain what a "G2 row" actually contains and what the key/value shape means; it does neither. For a data-retrieval tool an agent cannot predict the response or decide between it and latest_cpi.

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 the single access_token parameter is fully documented in the schema itself. The description adds nothing about the token or its optionality (required count is 0), so baseline 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?

"Full latest G2 row as key/value" gestures at a resource and a return shape, but "G2" is undefined jargon and there is no verb to say what the tool actually does (fetch? compute? return?). Against siblings like latest_cpi and cpi_history an agent cannot tell what distinguishes this tool.

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 versus latest_cpi, latest_groups, or cpi_history. The only hint is "PRO.", which suggests a paid-tier gate but not a selection 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?

No annotations are provided, so the description carries the full burden. The bare 'PRO' prefix hints at a paid/subscriber tier but never explains the access_token requirement, what happens without it, or how substring matching resolves (case sensitivity, ambiguity, empty results).

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 tight fragments with no filler, and the core scope (latest value, substring lookup) is front-loaded. The 'PRO.' prefix is cryptic but takes little space.

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 one of two parameters undocumented, the description should clarify auth/tier requirements and what a result contains. Instead it offers a single line, leaving the agent to infer subscription gating and return shape.

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?

Only half the parameters are described in the schema, and the description does add real meaning for the undocumented `name` parameter: it is a substring, not an exact match, with concrete examples (Food, Housing). That partly compensates for the coverage gap but leaves matching rules unspecified.

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 resource (an expenditure group's latest value) and constrains the lookup to a name substring, but it never states the domain is inflation and does nothing to distinguish it from siblings like latest_groups or inflation_full_latest. An agent can guess the intent but must infer the domain from the tool name alone.

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 versus latest_groups (which likely enumerates group names) or inflation_full_latest. The substring-matching behaviour is implied by 'name substring' but the agent is not told what to do when a partial name matches several groups.

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 does disclose two useful traits: the call is free (no cost/quota concern) and the payload is partial ('first columns'). It says nothing about refresh cadence, units, date coverage, or what the truncated columns contain.

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 fragments with no filler, but the lead token 'FREE' is a pricing note rather than the core purpose, and the terseness leaves key facts ('first columns' of what, at what granularity) unexplained.

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 parameters, and no output schema, the description is the only source of behavioral and return-value information, and it does not say what the indicators are, what format they return in, or how 'first columns' compares to activity_full_latest.

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 nothing for the description to disambiguate. Baseline 4 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?

Names a resource (RBA monthly activity indicators) but the verb is only implied and 'first columns' is cryptic without domain knowledge. It hints at a truncated preview relative to siblings like activity_full_latest, but never names or contrasts with them explicitly.

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?

No statement of when to use this versus activity_full_latest or activity_indicator. The phrase 'first columns' weakly implies a lightweight preview, but the agent must infer that a fuller-column sibling exists and when to prefer it.

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, but the zero-parameter shape combined with 'observation' makes it evidentially a read-only fetch. The description adds the useful 'FREE' cost/licensing signal, yet never states the operation is non-mutating, whether it requires auth, or how fresh the figure is.

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 fragments, no waste, with the cost signal front-loaded and the resource named immediately. Slightly telegraphic, but nothing extraneous.

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 no-argument single-observation tool with no output schema, the description gives enough for correct invocation. Only the return shape and freshness/lag semantics are left implicit, which is a minor gap 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?

The tool takes zero parameters, so the baseline is 4. The description correctly implies no input is needed — it is a parameterless fetch — with no gaps to compensate for.

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 and scope: the latest ABS headline CPI observation for Australia. An agent can tell what data comes back. It does not distinguish itself from siblings like cpi_history or inflation_full_latest, which cover overlapping CPI territory, so a 5 isn't earned.

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 only implied by the word 'latest' — the agent must infer that historical series belong to cpi_history and metadata to cpi_meta. There is no explicit when-to-use statement or named alternative.

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 does disclose two useful traits: zero cost ('FREE') and freshness ('Latest'). However, it does not say whether this returns a single row or a set, what the 'summary columns' actually contain, or anything about data currency beyond 'latest'.

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 fragments with the cost signal front-loaded and no wasted prose. The terseness borders on cryptic ('expenditure-group row'), but 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-parameter read with no output schema, the description should say what the returned row covers; 'summary columns' is a gesture rather than an explanation. Given the low complexity this is adequate but leaves the agent guessing about the payload.

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 the baseline is 4; there is nothing for the description to disambiguate. The phrase 'summary columns' loosely frames the output shape but no parameter semantics are 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 the specific resource (RBA inflation expenditure-group row) and qualifies it as the latest snapshot with summary columns, which implicitly separates it from the fuller inflation_full_latest. It stops short of naming a sibling explicitly, and 'expenditure-group row' is domain jargon an agent may not resolve without the schema.

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 leading 'FREE' token signals a cost-based selection rationale, and 'Latest' implies a snapshot use case, but there is no explicit when-to-use or when-not-to-use guidance relative to inflation_group or inflation_full_latest. Usage must be inferred.

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