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

No annotations provided, so description carries full burden. It describes the return value in detail (DatasetDetail with fields) and implies it is a read-only introspection. However, it doesn't explicitly state idempotency or lack of side effects, but the description is sufficient for this simple tool.

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?

Description is concise: two paragraphs. First sentence states purpose, second gives usage guidance, third details return values. No unnecessary words, well-structured.

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 simple one-parameter tool and existence of an output schema, the description is fairly complete. It explains the return fields (dimensions, measures, source_url, etc.) and usage context. Could mention safety but not necessary.

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% with examples and description. The description adds context by explaining that the parameter identifies a curated dataset and that the result helps inform subsequent get_data calls. This goes beyond the schema's basic description.

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?

Clearly states 'Describe a dataset's filterable dimensions, returnable measures, units, and source.' Uses specific verb 'describe' and resource 'dataset', and distinguishes from siblings like 'get_data' by stating 'Use this before calling get_data on a new dataset'.

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 tells when to use: 'Use this before calling get_data on a new dataset'. Also explains what it provides (valid filter keys, values, measure aliases, source URL). Doesn't explicitly state when not to use, but the guidance is clear.

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. It discloses that the tool returns a DataResponse with records/csv, unit, period bounds, row_count, source URL, and CC-BY attribution. It also mentions truncation behavior with 'truncated_at'. However, it does not address error handling, rate limits, or authentication requirements, which are minor gaps for a read-only query tool.

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 well-structured with a clear purpose statement, multiple examples with comments, and a return value summary. It is front-loaded with the core purpose. While slightly lengthy, each section (examples, return description) earns its place without extraneous 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?

Given 7 parameters, 100% schema coverage, and an output schema (mentioned in return description), the tool description is complete. It explains how to discover dataset IDs using 'search_datasets() / list_curated()', and describes the return structure. The examples cover common use cases (filtering, limiting, choosing format). Minor omission: no discussion of pagination or handling large responses beyond truncation.

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 all 7 parameters well. The description adds value through examples that illustrate parameter usage (e.g., filters, measures, limit) but does not introduce new semantic information beyond the schema examples. Baseline 3 is appropriate as the description complements but does not exceed the schema's coverage.

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 explicitly states 'Query a curated ATO/ACNC dataset and return observations.' The verb 'Query' and resource 'curated dataset' are specific. Multiple examples demonstrate usage with different datasets and parameters, clearly distinguishing it from sibling tools like 'describe_dataset' (describes schema) and 'search_datasets' (finds datasets).

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 provides examples that imply usage scenarios (e.g., filtering by state, limiting records) but does not explicitly state when to use this tool versus alternatives. No exclusions or when-not-to-use guidance is given, leaving the agent to infer context from examples 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?

With no annotations, the description fully carries the burden of transparency. It details behavior for two dataset types, mentions truncation via DataResponse.truncated_at, and explains the impact of the limit parameter. No contradictions occur.

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 with two paragraphs and a code example. No unnecessary sentences; every line contributes meaning.

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's complexity (handling two dataset types) and the presence of output schema, the description is complete. It covers behavior, examples, and limit guidance sufficiently.

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%, so baseline is 3. The description adds value by explaining limit behavior per dataset type and truncation. References to get_data for filters and measures are adequate.

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 that the tool returns the most recent observation(s) per measure for a dataset. It distinguishes between transposed time-series tables and wide register-shaped tables, and provides concrete examples. This specificity differentiates it from siblings like get_data.

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 when to use the tool (for latest observations, especially for time-series) and contrasts behavior with get_data. However, it lacks explicit 'when not to use' statements or alternative tool referrals.

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 provided, the description carries the full burden of behavioral transparency. It discloses that the tool returns a sorted list of dataset IDs and that each ID is documented via describe_dataset. However, it does not mention any potential side effects, authentication needs, or performance characteristics, but for a read-only listing operation, this is adequate.

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, consisting of four sentences. It front-loads the main purpose, then provides supplementary context, and ends with the return format. Every sentence adds value 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?

Given the simple nature of the tool (no parameters, straightforward output), the description is complete. It explains the purpose, the meaning of 'curated', the documentation reference, and the return format (sorted list). The presence of an output schema fills in any additional details about the return structure.

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 no parameters, so the schema provides no details. The description adds meaning by explaining what 'curated' means (datasets that accept plain-English filter keys in get_data and return aliased, well-typed measure columns). This adds semantic value beyond the empty 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 the tool's purpose: 'List every curated dataset ID in this version of ato-mcp.' It specifies the verb 'list', the resource 'curated dataset IDs', and the scope 'in this version'. Additionally, it distinguishes from sibling tools like search_datasets by explaining that these are the datasets where get_data accepts plain-English filter keys.

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?

While the description does not explicitly say when not to use this tool, it provides implicit guidance by explaining that this tool lists datasets that support plain-English filter keys in get_data. This helps an agent decide when to use this tool versus search_datasets or other listing tools.

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 explains it is fuzzy-search, case-insensitive, matches against multiple fields, returns ranked results with specific fields. It does not cover edge cases (no results, errors) or performance, but is transparent enough for typical use.

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, front-loaded with the main purpose, followed by context, examples, and return type. Every sentence adds value, and the structure is easy to parse.

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, the description covers the search behavior and return fields adequately. It could mention the default and maximum limit, but overall it provides enough context for an agent to use the tool 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 coverage is 100%, so baseline is 3. The description repeats schema info (e.g., 'Free-text search query' and limits). It adds no new semantic meaning beyond what is already in the input 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 the tool does 'Fuzzy-search the curated ATO/ACNC dataset catalog', which is a specific verb and resource. It distinguishes itself from siblings like describe_dataset or get_data by focusing on search and discovery. The examples further clarify the purpose.

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 provides relevant examples and mentions the catalog contents, but does not explicitly state when to use this tool vs alternatives (e.g., list_curated may be for listing without a query). The guidance is adequate but lacks exclusion criteria.

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?

Despite no annotations, the description discloses key behaviors: return shape (with/without group_by), grouping cap at 200 groups with truncation flag, and metadata in response. It does not explicitly state idempotency or read-only nature, but the operation is clearly a read. Slight missing on side effects or auth needs, but adequate.

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 well-structured with an intro, bulleted examples, and a return section. It is fairly long but every part adds value. Slight redundancy in the example formatting, but overall good balance of detail and conciseness.

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 number of parameters and existence of output schema, the description covers main behavior, return types, and grouping semantics. It lacks error handling or edge cases like empty results, but these are minor. The output schema likely fills gaps. Adequate for effective use.

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% with good descriptions. The description adds value beyond schema by providing concrete usage examples, clarifying group_by behavior and return structure. It explains what each parameter does in context, such as the meaning of group_by and the 'same envelope metadata' in returns.

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 'Aggregate statistics (count, sum, mean, median, min, max, stddev) for one measure across all rows matching filters' with a specific verb and resource. It distinguishes itself from siblings like get_data (raw data) and top_n (top values) by focusing on aggregation and grouping.

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 provides explicit guidance on when to use group_by vs without, includes examples showing single aggregate vs per-group statistics, and mentions that group_by is 'much more powerful for distribution X by Y queries that would otherwise require N filtered calls.' It implicitly tells when not to use it (when raw data is needed) via sibling context.

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 fully discloses behavior: server-side ranking, returning only requested rows, sorted output, and return structure matching get_data. No contradictions.

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 well-structured with an intro, rationale, examples, and return explanation. Every sentence adds necessary context 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?

Given 100% schema coverage and an output schema, the description covers all necessary aspects: purpose, usage, parameters, examples, and return format. No 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?

Schema coverage is 100%, baseline 3. The description adds value by explaining 'plain-English measure key', direction semantics, and providing detailed examples for each parameter.

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 it returns the top/bottom N rows by a measure, with explicit examples. It distinguishes itself from get_data by noting it avoids wasteful token usage.

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 states when to use (most common agent workflow) and contrasts with get_data as an alternative. However, it does not explicitly list 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.