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

No annotations are present, so the description carries the full behavioral burden. It does so well: it discloses that the data is returned inline as text, that parquet is base64-encoded because this is not a file-download channel, and that there is a hard cap of 5000 rows regardless of the requested limit. These are non-obvious runtime characteristics an agent needs to know before calling.

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?

Three sentences deliver the purpose, the unusual output behavior, and the fallback path – all in a front-loaded, focused structure. 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?

With no output schema and no annotations, the description still covers the return format, encoding nuance, row cap, and a pagination alternative. The schema covers parameter specifics, so the description is complete enough for an agent to invoke the tool correctly and set expectations.

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 high at 83%, and each parameter already has a meaningful schema-level description. The tool description does not materially extend parameter semantics beyond what the schema already documents, 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 action ('export rows') applied to a concrete resource ('a dataset') and explicitly enumerates the supported serialization formats (csv, json, geojson, parquet). It also distinguishes this from sibling tools by naming query_records as the alternative for larger datasets, so an agent can select it without opening every 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?

It gives clear when-to-use and when-not-to-use guidance: use this for exporting, and for larger datasets either narrow with where/select or switch to query_records with offset-based pagination. This directly addresses the main selection ambiguity among the sibling 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 provided, the description carries the full burden of disclosing behavior. It states it returns metadata and field schema, implying a read operation, but does not explicitly declare read-only status, error handling, or any side effects. For a simple fetch tool this is acceptable but not exemplary; more transparency about what happens on invalid IDs would improve 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?

The description is a single, well-structured sentence that leads with the primary purpose and immediately follows with the key output details. No filler or redundant phrasing; every clause adds value, making it highly efficient.

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 single-parameter tool with no output schema, the description explains the returned content (full metadata, field schema) and why it's needed (query expression writing). It lacks explicit return structure details, but 'full metadata' covers the breadth. Given the tool's simplicity, this is sufficiently complete.

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 provides a complete description of datasetId with an example, so schema coverage is 100%. The tool description does not add additional parameter semantics beyond that, but it does reinforce the purpose by linking the parameter to the returned schema. Baseline 3 is appropriate since the schema already handles the meaning.

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 'Get', the resource 'full metadata for a single dataset', and the identifier 'dataset_id'. It explicitly names the output (field schema with name, type, label, description) and its purpose for writing query expressions, which distinguishes it from siblings like search_datasets or query_records without ambiguity.

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 explicitly ties usage to preparing for query_records by mentioning the need for field schema in select/where/order_by expressions. This gives clear context for when to use it, though it doesn't explicitly state when not to use it (e.g., for searching datasets, which would be search_datasets). The guidance is implicit but strong.

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 are absent, so the description carries the behavioral burden. The verb 'get' implies a read-only operation and the description states it returns counts, but it does not disclose pagination, privacy scoping, or any side effects. It gives useful contextual positioning but stops short of a full behavioral profile.

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 two sentences with no fluff. The functional purpose is front-loaded, followed by a succinct, non-repetitive usage directive. Every word 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's low complexity—three parameters, one required, no nested objects, and no output schema—the description is largely sufficient. It conveys the tool's purpose, return content, and the immediate usage context, leaving only peripheral details like error behavior or pagination unexplained.

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 mentions 'where' and 'refine' filters only to explain the return value's purpose; it does not add new semantics or formats for those parameters beyond what the schema already provides.

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-resource pair ('Get facet values and their record counts') and confines the scope to a dataset's filterable fields. It also distinguishes the tool from query_records by saying it should be called first, which disambiguates it from siblings.

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 explicitly instructs when to call the tool ('Call this before query_records') and why, to discover valid filter values 'instead of guessing.' This is a clear, actionable usage directive that names the correlated sibling and the problem avoids.

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 disclosure burden. It usefully reveals pagination behavior and the optional geom field for geographic datasets, but it does not mention response shape, error or rate-limit behavior, or the read-only nature beyond the word 'Query'.

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?

Three sentences with no filler: the core capability is stated first, followed by a useful output caveat and a practical prerequisite. The structure is front-loaded and each 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 a 9-parameter query tool with no annotations and no output schema, this description does solid work: it explains the query language, pagination, a special output field, and a preparation step. The main gap is not addressing when to choose export_dataset to pull a full dataset instead.

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 78%, so the schema already explains most parameters. The description adds that limit/offset handle pagination and that the ODSQL clauses are where/select/order_by/group_by/q/refine, but it does not substantially deepen the meaning of any individual parameter beyond what the schema provides.

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 is specific about the verb and resource: it queries and filters records within a dataset using ODSQL, and it lists the main query clauses. It clearly targets record-level access rather than dataset-level operations, but it does not explicitly contrast with export_dataset, so a little ambiguity remains.

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 gives a clear, actionable prerequisite: call get_dataset first if field names are unknown. However, it does not explicitly say when to prefer export_dataset or get_facets over this tool, so exclusions and alternative routing are incomplete.

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 says 'Search/list' which strongly implies a read-only operation, and it states the return fields. However, it does not explicitly declare that the operation is non-destructive or that it does not modify data. It also does not mention any rate limits, permissions, or error behavior. The description is adequate but not comprehensive for a tool with no annotation coverage.

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 a single compact sentence that front-loads the core purpose ('Search/list datasets'), then specifies supported search modes and return fields. There is no redundant or filler content; every clause contributes useful 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 search tool with five parameters and no output schema, the description covers the purpose, supported parameters (q and where), and return fields. It does not explicitly explain pagination via limit/offset or ordering via orderBy, but those are defined in the schema. It is complete enough for an agent to understand what the tool does and what it returns, though it could add a note about pagination behavior.

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 60%: q, where, and orderBy have descriptions; limit and offset only have defaults. The description adds context for q and where (full-text search and ODSQL boolean filter), and clarifies that they can be used together ('and/or'). It does not mention limit or offset, and does not fully compensate for the missing descriptions. The added value over the schema is moderate.

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 'search/list' and the resource 'datasets in the City of Vancouver Open Data Portal catalog'. It also enumerates the returned fields, making the tool's purpose unambiguous. The focus on searching/listing datasets distinguishes it from siblings like get_dataset (single dataset retrieval), query_records (records within a dataset), get_facets, and export_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?

The description implies when to use the tool: when you need to search or list datasets, optionally using full-text search or an ODSQL filter. It does not explicitly name alternatives or state when not to use it, but the context is clear. It does not say 'use this instead of get_dataset', but the distinction is evident from the description's scope.

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