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

Annotations already declare destructiveHint=true, readOnlyHint=false, and openWorldHint=false, so safety profile is covered. The description adds genuine behavioral context about unqualified name resolution, which is not in the annotations, but it never warns that arbitrary SQL can mutate or drop data — a meaningful omission for a destructive 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?

Three tightly written sentences, front-loaded with the core action, followed by the naming-resolution rules. No filler or repetition.

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?

An output schema exists, so return values need not be explained, and the description adequately covers invocation semantics. It could go further by noting that the tool executes arbitrary statements including writes/DDL, but the destructiveHint annotation already signals that.

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?

With one parameter at 100% schema coverage the baseline is 3, but the description adds real meaning beyond 'SQL query to execute' by explaining how unqualified versus fully qualified table names resolve against current_database()/current_schema(). That directly informs how the agent should author the sql argument.

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: 'Execute a SQL query on the DuckDB or MotherDuck database', which is immediately distinguishable from the introspection siblings (list_databases, list_tables, list_columns). It does not explicitly name or contrast with those siblings, so it falls 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?

The description gives useful conditional guidance about when fully qualified names are needed ('only needed when multiple DuckDB databases are attached or when connected to MotherDuck'), but that is guidance about writing the SQL, not about when to choose this tool over switch_database_connection or the listing tools. Usage context is implied rather than 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?

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds the useful defaulting behavior for database/schema, but that same default is already stated in the input schema, so the incremental behavioral value is modest.

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, front-loaded with the core purpose, and the defaulting constraint follows without redundancy or wasted words.

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 annotations covering safety and a full output schema covering return values, the description supplies the only remaining critical context: that database/schema fall back to the current session. Nothing needed to call this tool correctly 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 all three parameters, including their defaulting behavior. The description repeats the database/schema default without adding syntax, format, or selection meaning beyond the 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?

States a specific verb and resource: 'List all columns of a table or view with their types and comments.' This clearly distinguishes it from sibling tools like list_tables and list_databases, and an agent can tell exactly what it returns.

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 purpose implies usage (inspect table structure), and the description notes the default database/schema behavior, but it never states when to choose this over execute_query or list_tables, nor any prerequisites or exclusions. Adequate but with a clear gap in routing 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, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered. The description adds only the MotherDuck/multi-attach scenario and says nothing about result ordering, pagination, or scope limits beyond 'the connection'.

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 sentences with the core action front-loaded and the situational hint second. Nothing is redundant or padded.

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 zero params, rich annotations, and an output schema that handles return values, the description covers what an agent needs. It could be marginally stronger by clarifying that it lists databases within the active connection rather than across all connections.

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 schema carries no parameter semantics to explain; baseline for a no-arg tool is 4. The description correctly implies no filtering inputs are required.

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 (List) and resource (databases) scoped to the current connection, which cleanly separates it from list_tables and list_columns. It does not explicitly name a sibling to route against, but the resource noun is unambiguous.

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 usage condition ('when multiple DuckDB databases are attached or when connected to MotherDuck'), which is real implied guidance. However, it never says when NOT to use it or which sibling to pick instead (e.g., list_tables for table enumeration), so guidance stays implicit.

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, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description only adds that comments accompany each table and that the current database is the default scope; it says nothing about result size, filtering interaction, or pagination.

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 sentences, zero filler, with the primary action stated first and the fallback behavior second. Nothing redundant or padding.

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?

An output schema exists, so return values need not be explained, and the tool is a simple read with no credentials or side effects. The definition is essentially complete, with only minor room for a note on result limits or when to prefer list_columns.

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 both the 'schema' filter and the 'database' default are already documented in the schema. The description merely restates the database default, adding no format, syntax, or edge-case detail beyond the 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?

States a specific verb (List) and resource (tables and views in a database) with the added detail that comments are returned. The resource clearly separates it from siblings like list_databases and list_columns, though no sibling is named 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?

The description explains a default (falls back to the current database) but gives no guidance on when to choose this tool over list_databases, list_columns, or execute_query. Usage must be inferred entirely from the name.

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 only declare readOnlyHint=false, openWorldHint=true and destructiveHint=false. The description adds real behavioral context beyond that: the new connection inherits the server's read/write mode, and creating a missing file is gated on read-write mode. It does not state what happens to the previous connection or whether switching mid-transaction is permitted, so this is strong but not complete.

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 short sentences, purpose first, then constraints in descending order of importance. No filler, no repetition of the title, and the preconditions are front-loaded where an agent will see them.

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?

An output schema exists, so return values need not be explained, and the main surprising preconditions (absolute paths, file existence, read-write mode) are covered. The one notable omission is the fate of the previously active connection, which matters for a state-switching tool.

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 absolute-path requirements and the create_if_not_exists read-write constraint. The description largely restates those same facts, adding no syntax or format detail beyond the schema; 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?

States a specific verb and resource ("Switch to a different database connection"), which no sibling tool does — the siblings are all query/catalog tools. However, it never names or contrasts with any alternative (e.g., list_databases to discover targets), so it is clear but lacks explicit sibling differentiation.

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 conditional usage rules (absolute paths for local files, create_if_not_exists=True only in read-write mode), which is genuine guidance. But it never says when to prefer this tool or how to find valid targets, leaving the agent to infer that from siblings like list_databases.

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