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

No annotations are provided, so the description must carry the full burden of behavioral disclosure. It does not state that the operation is read-only, whether it requires specific permissions, or what happens if the table does not exist. The description only conveys the basic action without side effects or constraints.

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 extremely concise, with only two sentences. It front-loads the main purpose and then lists parameters in a standard format. Every word earns its place with no 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 that an output schema exists, the description does not need to detail return values. However, it lacks mention of error handling or behavior for missing tables. The tool is simple, so the completeness is borderline adequate but could be improved.

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 has no descriptions (0% coverage), so the description's annotation of each parameter as a 'plain identifier' adds meaningful context beyond the schema. This clarifies that identifiers should not be quoted or schema-qualified, which helps the agent properly invoke the tool.

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: 'Return column types for a table,' which is a specific verb-resource combination. It is easily distinguished from sibling tools like get_sample_data or list_tables, which perform different operations.

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 no guidance on when to use this tool versus alternatives. It does not mention prerequisites, such as requiring an existing database or table, nor does it advise against using it for retrieving actual data.

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 provided, so description carries full burden. Discloses limit clamping to [1,1000], which is a key behavioral trait. Does not mention potential errors or that the operation is read-only, though that is implied. Adding a note about ordering or error handling would increase transparency.

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?

Short and to the point, using a structured Args format. Every sentence adds value. Minor reduction because the Args block is somewhat verbose for a simple tool, but overall 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?

Given the tool's simplicity and presence of output schema, description covers essential aspects: purpose, parameters, limit clamping. Lacks mention of result ordering (e.g., arbitrary) or error handling for missing tables. Still adequate for most use cases.

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 0%, so description must compensate. Adds meaning to all three parameters: explains 'database' and 'table' as plain identifiers, and documents limit clamping behavior. However, does not define 'plain identifier' (e.g., case sensitivity), so slight gap remains.

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 it returns the first N rows of a table, which is a specific verb+resource. Differentiates from sibling tools like query (arbitrary SQL) and describe_table (schema retrieval) by specifying a limited preview.

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?

Indirectly implies use for quick sampling ('first N rows'), but does not explicitly state when not to use it (e.g., for full queries use query) or provide alternatives. Could be improved by mentioning that query supports arbitrary SQL.

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 missing annotations, the description explicitly states the output format ('TabSeparated format') and the scope ('visible to the chDB session'), providing useful behavioral detail beyond a simple list operation.

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 concise sentences front-load the purpose and add a critical output detail. No 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 the tool's simplicity (no parameters, straightforward list operation) and the presence of an output schema, the description fully covers what an agent needs: what it lists and the return format.

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 0 parameters and 100% schema coverage, the description correctly adds no param details. For zero-parameter tools, the baseline is 4, and the description meets that.

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 'List databases visible to the chDB session' with a specific verb and resource. Differentiates from sibling tools like list_tables or list_functions by focusing solely on databases.

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 use this tool versus alternatives. Without context on when listing databases is appropriate or how it differs from other list tools, the agent lacks decision support.

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 full burden. It explains the read-only behavior, returned fields, and filter semantics (case-insensitive, no wildcards). Missing details on permissions or error handling, but adequate for a list operation.

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 a front-loaded purpose and a clear Args section. Every sentence adds value with no 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?

Given the low complexity, an output schema exists, and the description covers the returned fields and filter behavior, it is 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 schema has 0% description coverage, but the description fully explains the 'pattern' parameter's behavior (case-insensitive substring, plain text only, wildcards escaped), adding significant value 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?

The description clearly states it lists SQL functions, specifies the returned fields (name, is_aggregate, etc.), and distinguishes from sibling tools which deal with tables, databases, queries, etc.

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 a use case (discovering functions in one round trip) but does not explicitly state when to use vs alternatives or when not to use.

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 one behavioral trait: the database parameter must be a plain SQL identifier. However, it does not disclose other important behaviors like read-only nature, permission requirements, or whether only visible tables are returned. With no annotations, the description carries the full burden and partially meets 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 concise with two sentences, no wasted words, and the primary action is stated first. Every sentence adds value.

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 (one parameter) and the presence of an output schema, the description is nearly complete. It explains the tool's purpose and parameter constraints. A minor gap is the lack of mention of return format, but that is covered by the output schema.

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 has 0% description coverage, but the description fully compensates by specifying the database parameter's format (plain SQL identifier) and providing concrete constraints (letters, digits, underscore, no quotes, dots, or spaces), adding significant 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?

The description clearly states the tool lists tables in a given database using a specific verb and resource, and it is easily distinguishable from sibling tools like list_databases (lists databases) and describe_table (describes a specific table).

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 no guidance on when to use this tool versus alternatives, such as prerequisites (e.g., need to know database name first) or exclusions (e.g., cannot list tables across databases).

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 fully discloses behavioral traits: result truncation limit (CHDB_MCP_MAX_RESULT_BYTES), query timeout (CHDB_MCP_QUERY_TIMEOUT_SEC), write permission requirement (CHDB_MCP_WRITE=1), and safety restrictions for external functions under CHDB_MCP_FILE_ALLOWLIST.

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 and concise, using a paragraph for core usage and bullet points for details. Every sentence provides necessary information without redundancy, making it efficient for an agent 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 complexity of executing arbitrary SQL with security constraints, the description is remarkably complete. It covers execution limits, write permissions, file allowlist restrictions, format options, and the existence of an output schema reduces the need to explain return values.

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 0%, but the description compensates thoroughly. The sql parameter is explained with read-only vs write usage, and the format parameter is described with default value and common formats list. This adds significant meaning beyond the bare 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 'Execute an arbitrary SQL statement against the chDB session' which is a specific verb+resource. It distinguishes from sibling tools like query_file by explicitly directing users to that tool for file operations.

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 this tool: for read-only SQL by default, with writes requiring a specific environment variable. It also notes that many table functions are rejected when a file allowlist is set, and directs users to query_file() for files, effectively differentiating from siblings.

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 full burden. It discloses file format support, placeholder substitution behavior, and security scanning/rejection of malicious SQL when allowlist is set. 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?

Well-structured with summary, example, and bulleted args. Slightly verbose (e.g., repeated allowlist explanations), but information density is high.

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?

Covers parameters, usage, and security comprehensively. Has output schema so return values are covered. Could mention error scenarios or performance implications, but given complexity it's fairly 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?

Schema coverage is 0%, but the description fully explains each parameter: path (with allowlist constraint), sql (must contain '{file}', scanning behavior), and format (hints with common values). This compensates for the bare 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 it queries local files (Parquet, CSV, JSON, etc.) as a table. It provides a concrete example with placeholders, distinguishing it from sibling tools like 'query' (which queries database tables) and 'describe_table'.

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 specifies when to use (querying local files) and explains the placeholder substitution and security allowlist. However, it does not explicitly contrast with alternatives or mention when not to use the tool.

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