oecd-mcp-server

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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the description's listing behavior is consistent and adds no contradiction. It adds context beyond annotations by revealing the dependency on a prior spill and the environmental requirement for duckdb. It does not detail output shape, but the presence of an output schema lowers the need for that.

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, each with distinct value: what it lists, when to call it relative to oecd_dataframe_query, and the only environment where it is available. The most actionable statement is front-loaded, 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?

For a single-parameter read-only metadata tool with a rich schema description and an output schema, the description fully covers what the agent needs: the object being inspected, the prerequisite spill, the ordering relative to the query tool, and the duckdb-only availability. No critical guidance 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 description coverage is 100%, and the canvas_id schema entry already explains its provenance ('Canvas ID returned by oecd_query_dataset') and referent ('DataCanvas session holding the staged observation tables'). The description reinforces this linkage but adds no new parameter-level meaning, so the baseline score 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?

Description opens with a specific verb and object: 'List tables and columns staged on a DataCanvas by a prior oecd_query_dataset spill.' It distinguishes itself from sibling oecd_dataframe_query by positioning itself as the pre-query discovery step, so an agent knows exactly what this tool does and which sibling it complements.

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 states when to use it: 'Call this before oecd_dataframe_query to discover exact table and column names for SQL.' It also names the prerequisite (prior oecd_query_dataset spill) and a hard restriction (CANVAS_PROVIDER_TYPE=duckdb), leaving no ambiguity about the invocation 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?

Beyond the readOnlyHint and idempotentHint annotations, the description discloses important behavioral constraints: only SELECT statements are allowed, DDL/DML and file-reading functions are rejected, and the tool operates on tables staged by oecd_query_dataset. This adds meaningful safety and restriction context beyond what annotations already convey.

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, each carrying essential information: the core operation, required precursor and use cases, and a hard environment prerequisite. There is no filler or redundant restatement of the tool name or 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?

With a 100%-covered schema, an output schema present, and annotations already signaling read-only/idempotent behavior, the description supplies the remaining critical context: the dependency on oecd_query_dataset, the need to call oecd_dataframe_describe first, and the DuckDB provider condition. An agent has enough information to invoke this 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?

Both parameters are already fully described in the schema (100% coverage), so the baseline is 3. The description adds value by explaining that sql should reference table names from oecd_dataframe_describe and that canvas_id identifies the DataCanvas session from oecd_query_dataset, reinforcing the relationship between parameters and workflow.

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 ('Run a read-only SQL SELECT'), names the target resource ('OECD observation tables staged on a DataCanvas by oecd_query_dataset'), and clearly separates this from sibling tools like oecd_dataframe_describe and oecd_query_dataset. It uses a concrete verb and resource, making the tool's role immediately identifiable.

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 usage context: call oecd_dataframe_describe first to learn table/column names, use this tool for aggregation, filtering, GROUP BY, JOIN, and window functions, and note that it is only available when CANVAS_PROVIDER_TYPE=duckdb is set. It does not explicitly enumerate when-not-to-use alternatives, but the prerequisite and environment condition provide solid operational guidance.

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, idempotentHint=true, and openWorldHint=true, so the safety profile is covered. The description adds value by disclosing that the tool returns key-construction information (position in the dot-delimited key) and that it is a prerequisite step, which is behavioral context beyond the annotations. It doesn't discuss rate limits or error cases, but for a read-only metadata fetch the annotations plus the description are sufficient.

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, each earning its place: the first states what the tool returns, the second details the return contents, and the third gives the usage context. The most important information (what it fetches and why it's needed) is front-loaded. No filler or repetition of schema details.

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?

The tool has one parameter, a rich schema description, an output schema, and annotations covering safety and idempotency. The description explains the return value's purpose and the prerequisite relationship to oecd_query_dataset. Nothing an agent needs to decide whether to call this tool and how to use its output 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 description coverage is 100%, so the schema already documents flow_ref thoroughly, including the two accepted forms and an example. The description adds context by explaining that the output is needed to construct query keys, which helps the agent understand why flow_ref matters. Since the schema does the heavy lifting, a 4 is appropriate rather than a 5.

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 ('Fetch'), a specific resource ('a dataflow's dimensions'), and the concrete output (dimension names, codelist references, position in the dot-delimited key). It also explicitly distinguishes itself from oecd_query_dataset by saying it is required before calling that tool to understand key structure. This clearly differentiates it from siblings like oecd_get_dimension_values and oecd_query_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 explicitly says 'Required before calling oecd_query_dataset to understand key structure,' which gives a clear when-to-use directive and names the alternative it supports. It also implies this is a prerequisite/metadata tool rather than a data-fetching tool, which helps an agent choose it over oecd_query_dataset or oecd_get_dimension_values. No exclusions are needed because the tool's role as a prerequisite is clearly stated.

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?

The description adds behavioral context beyond the readOnly/openWorld/idempotent annotations: responses are paginated at 'at most limit codes either way,' and codelists 'run to a thousand-plus entries,' explaining why querying and paging matter. No contradiction with annotations.

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 deliver purpose, usage context, a rationale for the query parameter, and pagination behavior. Everything earns its place and the key action 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?

Input schema fully documents parameters, an output schema exists, and the description supplies the workflow context and pagination behavior. It is complete for practical use, though explicit alternative tool guidance would make it stronger.

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 the baseline applies. The description adds workflow context but does not materially elaborate on individual parameter meanings beyond what the schema already documents, so it neither compensates nor needs to.

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: 'Fetch the valid codes and labels for one dimension of a dataflow.' It also frames the tool's role in the workflow, resolving human-readable names to SDMX codes before using oecd_query_dataset, which differentiates it from sibling tools.

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?

Clear context is provided: use this tool to resolve names to codes before querying with oecd_query_dataset. It does not enumerate exclusions or alternative tools explicitly, but the intended position in the workflow is unambiguous.

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, idempotentHint, and openWorldHint, so the safety profile is covered. The description adds value by naming the returned content (agencies, directorate, dataflow counts) and its intended role in a search workflow. It does not go further into behavior such as pagination, ordering, or how open-world results should be interpreted, but for a zero-parameter list tool this is sufficient.

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 no filler. The first sentence states what the tool returns, and the second gives the concrete workflow purpose. Every word earns its place and the key action 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 zero-parameter, read-only, idempotent listing tool with an output schema present, the description covers the essential information: what is returned and why an agent would invoke it. The annotations handle side-effect concerns, and the output schema handles return structure details.

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 zero parameters, so the input schema is complete by definition and there is nothing for the description to clarify. Baseline for no-parameter tools is 4, and the description appropriately avoids inventing parameter information that does not exist.

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 opens with a specific verb and resource ('List OECD SDMX agencies') and specifies the exact output fields ('directorate each belongs to, and the number of dataflows each publishes'). It differentiates itself from siblings by positioning itself as the precursor to filtering oecd_search_datasets, so an agent can distinguish it without opening 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 description gives an explicit use case: discover agency IDs before filtering oecd_search_datasets by department. It names the sibling tool and the workflow context. It does not explicitly state when not to use it, but the positive guidance is specific enough to route an agent effectively.

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?

The description adds meaningful behavior beyond the annotations: rows are decoded with labels, values are scaled by the observation unit multiplier, large results spill to DataCanvas, and without DataCanvas every row still returns but the rendered table preview is sliced. No contradiction with the readOnly, openWorld, or idempotent hints.

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 dense sentences deliver the core action, return behavior, spill handling, and prerequisite in order. Every clause earns its place with no redundancy or fluff.

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 detailed input schema, annotations, and output schema, the description covers what the tool returns, how result size behaves, what to do for large spills, and what to call beforehand. An agent has enough context to invoke this tool correctly and route to siblings when appropriate.

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 each parameter already has a detailed explanation, so the description does not need to repeat parameter-level semantics. The main description adds context around result behavior rather than new parameter meaning, which matches the baseline of 3.

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: it fetches observations from an OECD dataflow filtered by dimension key and optional time range. It differentiates itself from siblings by explicitly naming the prerequisite oecd_get_dataset_info and the follow-up oecd_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 explicit usage context: call oecd_get_dataset_info first to learn dimension order, and follow up with oecd_dataframe_query when large results spill to a DataCanvas table. This tells an agent when this tool fits into a multi-step workflow versus when another sibling is needed.

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 readOnly, idempotent, and openWorld behavior, so the description only needs to add context. It adds the matching behavior (against names and descriptions) and the specific return payload, which is useful beyond the annotations. No contradiction with the annotation hints.

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 no filler; the search action and matching scope are front-loaded, and the return-value note is relevant to downstream tool selection.

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 read-only search tool with a fully documented schema, rich annotations, and an output schema, the description covers the necessary selection and invocation context. It tells the agent what to expect and how the result connects to oecd_get_dataset_info.

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 input schema already documents query, limit, offset, and agency_id with examples and constraints. The tool description adds no parameter-level meaning, so the 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?

The description specifies a concrete action (search OECD dataflows by keyword or theme), the matching target (dataflow names and descriptions), and the returned identifiers (flow_ref, names, agency IDs). It also positions the tool as the discovery step preceding oecd_get_dataset_info, distinguishing it from sibling query/dataframe tools.

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 makes the intended workflow clear: search by keyword or theme to obtain identifiers 'for use with oecd_get_dataset_info.' It does not explicitly list when not to use it or name alternatives, so it stops short of full exclusion guidance.

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