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

With no annotations, the description carries the full burden. It discloses the backup method (online backup API), consistency guarantee, WAL inclusion, and auto-timestamp behavior. However, it does not specify side effects like file overwrite behavior or blocking.

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?

A single, efficient sentence that front-loads the safety indicator and covers all key aspects: purpose, method, included data, and automatic naming. 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 simplicity (2 optional params, no output schema) and 26 siblings, the description covers the essential behavioral and usage context. It lacks return value details, but for a straightforward backup tool this is acceptable.

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%, so the description must compensate. It explains backup_path is optional (auto-timestamped) but does not clarify source_database_name beyond its name, leaving its purpose ambiguous (likely the current database). Partial 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?

Tautological: description restates name/title.

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 includes a safety indicator ('✓ SAFE') but provides no explicit guidance on when to use this tool versus alternatives like vacuum_database or export_csv. Usage context is only implied through the safety marker.

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 mentions 'holds locks until commit/rollback', which adds behavioral context beyond a simple 'begin transaction'. However, with no annotations, more details (e.g., timeout, nesting, impact on other connections) would be beneficial. The description does not contradict any annotations as none are provided.

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 very concise, but it repeats the title verbatim. It front-loads the purpose but does not add new information beyond the title. It could be more structured and earn its length.

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 description is inadequate given the tool's complexity (transaction management, 26 sibling tools). It does not explain prerequisites (e.g., database must be open), default behavior if no database_name specified, or that transaction must be active for subsequent operations. No output schema or annotations to compensate.

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 only parameter 'database_name' is optional with no description. Schema description coverage is 0%, so the description provides no information about its purpose or default behavior.

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?

Tautological: description restates name/title.

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 executing queries without a transaction or versus other database tools. The description lacks context on prerequisites or typical usage patterns.

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 includes the warning 'DESTRUCTIVE' and specifies the default batch size and column constraint. However, it lacks details on transactionality, error handling, return value, or whether the operation is atomic, which are critical for a potentially destructive tool with no 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?

The description is short (two sentences) and front-loads the critical warning. It is efficient but could be improved by adding more behavioral context without becoming verbose.

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 (4 params, no output schema, no annotations), the description is insufficient. It fails to explain return values, error scenarios, performance characteristics, or batch behavior, leaving the agent underinformed for correct invocation.

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 description adds meaning for two parameters: data (must have identical columns) and batch_size (default 1000). However, it does not explain table or database_name beyond what the schema provides. With 0% schema coverage, the description partially compensates but leaves gaps.

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?

Tautological: description restates name/title.

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 explicit guidance on when to use this tool versus alternatives (e.g., execute_write_query for single inserts). The description implies use for batch inserts but does not provide conditions, prerequisites, or contraindications.

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 discloses the action (close connection, free resources) and its non-destructive nature. However, it omits details like whether it commits pending transactions, idempotency, or error behavior. Annotations are absent, so the description carries full burden but only partially fulfills 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 extremely short with no fluff, but it repeats the title verbatim. It is concise but could be slightly more informative without losing brevity.

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 lack of output schema, the description is adequate but not thorough. It doesn't state prerequisites (e.g., database must be open) or consequences, which would improve completeness.

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 optional database_name parameter is not mentioned in the description. With 0% schema description coverage, the description should explain its purpose (e.g., which connection to close). The omission leaves the agent guessing.

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?

Tautological: description restates name/title.

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 is provided on when to use this tool versus alternatives (e.g., after transactions, before closing app). The description only asserts safety, not context or exclusions.

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?

Without annotations, the description carries the full burden of disclosing behavior. It explicitly states 'making changes permanent' and 'Releases locks', which are key behavioral traits. However, it does not mention error conditions or the requirement of an active transaction.

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, concise sentence that conveys the essential purpose and effects without any wasted words. It is well-structured and front-loaded with the key action.

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 simplicity of the tool and the presence of related siblings, the description covers the basic semantic action but lacks details on parameter usage and preconditions. It is minimally adequate but has clear 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 description coverage is 0%, and the description adds no meaning to the single parameter 'database_name'. The parameter's purpose (e.g., which database's transaction to commit) is left entirely to the user to infer.

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?

Tautological: description restates name/title.

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 (to finalize a transaction) but provides no explicit guidance on when not to use it, prerequisites (e.g., an active transaction), or alternatives. This omission limits its helpfulness for decision-making.

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 creates a file, errors if the file exists, and suggests an alternative. It does not describe return value or side effects beyond creation, but the core behavior is well communicated.

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 very concise (two sentences plus a warning prefix) and front-loaded. Every sentence adds value: warning, action, error condition, alternative tool. No 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?

While the description covers the main purpose and error condition, it omits whether the created database is automatically opened for subsequent operations. Given sibling tools like 'open_database', this is an important gap. The tool has no output schema, so description should clarify return behavior or next steps.

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% schema description coverage, the description should compensate. However, it only mentions 'at the given path' without additional semantics (e.g., format, relative/absolute, file extension, directory existence requirements). The single 'path' parameter is not elaborated beyond 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?

Tautological: description restates name/title.

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 this tool (to create a new database) and when not to (if file exists), and provides an alternative tool 'open_database'. This gives clear usage 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?

Discloses that it is a schema change, fails if table exists, and supports constraints. No annotations present, so description carries full burden; could add more on permissions or irreversibility but 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?

Single sentence with a warning emoji front-loads key information. No redundant content, every word contributes to understanding.

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 creation tool with no output schema, description adequately explains purpose, constraints, and failure condition. Missing explanation of database_name parameter and context vs other DDL tools, but overall sufficient.

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?

Description adds context that primary keys, defaults, and NOT NULL are supported, mapping to column properties. However, it does not explain the 'database_name' parameter, and schema coverage is 0%. Partially compensates but incomplete.

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?

Tautological: description restates name/title.

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?

Implies usage for creating new tables, and notes 'Fails if exists' as a condition. No explicit guidance on when to use vs alternative tools like execute_schema_query or alter_table (if existed).

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. It explicitly states 'Metadata only, no data' and '✓ SAFE', clearly indicating the tool is read-only and non-destructive. This is sufficient for a metadata retrieval tool, though it could mention permission requirements or scope.

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, front-loaded sentence that conveys all key information without excess. It is perfectly sized for quick scanning by an AI agent.

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 has no output schema and only one optional parameter, the description provides basic return information (size, counts, statistics) but does not explain behavior when no database_name is provided (e.g., returns info for all databases?). An agent may need additional context for correct invocation.

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 one parameter 'database_name' with 0% description coverage, and the description does not mention this parameter at all. It fails to clarify whether the parameter is required, its default behavior, or how to use it. The description must compensate for low schema coverage but does not.

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?

Tautological: description restates name/title.

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 includes '✓ SAFE' which implies it is a read-only, low-risk operation, but it does not provide explicit guidance on when to use it versus sibling tools like 'list_databases' or 'describe_table'. The usage context is implied but not directly 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?

No annotations are provided, so the description carries full burden. It marks the tool as 'SAFE' but does not elaborate on whether it is read-only, idempotent, or requires any special permissions. For a read-only schema inspection tool, this is minimally acceptable but not explicit.

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 (one line) but at the expense of essential parameter context. While front-loaded with safety indication, it fails to earn its place by omitting necessary guidance.

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 no output schema, so the description should explain return structure; it partially does by listing schema components. However, it lacks explanation of how verbosity changes output and what database_name does. Given sibling complexity, the description is incomplete.

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% for parameters, and the description does not explain any of the three parameters (table, verbosity, database_name). It adds no meaning beyond the schema itself.

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?

Tautological: description restates name/title.

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 like execute_schema_query or list_tables. The description does not mention prerequisites or when not to use it.

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 effectively communicates the destructive, irreversible nature of the operation and explicitly lists what is removed. However, it lacks details on side effects (e.g., cascading drops of dependent objects) or performance implications.

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 very concise, front-loading a warning and listing effects in one sentence. It efficiently communicates the core, but could include parameter details without losing 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 simplicity of the tool (2 params, no output schema), the description is incomplete. It does not cover parameter meaning, prerequisites, error conditions, or return behavior. Presence of sibling tools like backup_database suggests missing workflow guidance.

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%, and the description does not explain the parameters 'table' and 'database_name'. While the names are somewhat self-explanatory, the description should add clarity, such as the exact format or permitted values. It fails to compensate for the lack of schema descriptions.

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?

Tautological: description restates name/title.

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 is provided on when to use this tool vs alternatives. It does not mention prerequisites (e.g., backing up), when not to use it, or context like needing to check dependencies. Among siblings, backup_database is a relevant alternative but not referenced.

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 partially covers behavioral aspects: safety, read-only nature, default row limit, and verbosity option. It does not disclose error handling, connection state requirements, or potential side effects, which is acceptable for a read-only query but not exhaustive.

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 efficient sentence, front-loading key details (SAFE, read-only, supported SQL types). Every clause serves a purpose, 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?

No output schema exists, so the description should explain return values or behavior. It mentions verbosity for counts but does not describe row output, pagination via offset, or prerequisites like an open database (hinted by sibling open_database). This leaves significant gaps for a 6-parameter 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 0%, so the description must compensate. It explains parameterized queries (params), default limit (limit), and verbosity ('summary' for counts). It omits offset, query, and database_name. This adds value but is incomplete.

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?

Tautological: description restates name/title.

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 implicitly guides usage by emphasizing read-only operations and mentioning parameterized queries and verbosity. However, it does not explicitly state when to avoid this tool or provide clear alternatives, though sibling names offer hints.

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 mentions that the tool modifies database structure and may lock tables, which warns of potential side effects. However, it does not disclose reversibility, permission requirements, or auto-commit behavior, leaving significant gaps.

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 (one sentence) but it is a direct copy of the title. Every word is present in the title already, so the description does not earn its place by adding 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 complexity (3 parameters, no output schema, subtle sibling distinctions), the description is grossly incomplete. It fails to clarify the query parameter, how to use params and database_name, or how it differs from other schema-altering tools.

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%, yet the description does not explain any of the three parameters (query, params, database_name). The agent receives no guidance on how to use these parameters, despite the tool's complexity.

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?

Tautological: description restates name/title.

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 usage guidelines are provided. The description does not specify when to use this tool versus siblings like create_table, drop_table, or execute_write_query, nor does it mention prerequisites or exclusions.

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 provides basic behavioral info: it modifies data (destructive), supports parameterized queries, and returns affected row count. However, it omits details on auto-commit behavior, transaction interaction, error handling, permission requirements, and side effects, which are critical 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?

The description is very short (one sentence plus a warning emoji), which is concise. However, it could include more useful parameter or usage information without becoming verbose, making it slightly under-informative for its length.

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 destructive tool with 3 parameters, no output schema, and sibling tools including transactions, the description is incomplete. It does not address how parameters like 'params' are used, the role of 'database_name', or whether the tool should be used within a transaction, leaving significant 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 description coverage is 0%, yet the description only adds 'parameterized queries' without explaining the 'params' object structure or 'database_name' parameter. The description does not compensate for the missing schema documentation, leaving the agent to infer parameter usage.

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?

Tautological: description restates name/title.

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 lacks any guidance on when to use this tool vs alternatives (e.g., execute_read_query for reads, begin_transaction for transactions). No prerequisites or exclusion criteria are mentioned, leaving the agent without context for appropriate invocation.

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 must cover behavior. It warns about file write and absolute paths, and restricts queries to read-only types. But it lacks detail on overwrite behavior, side effects of append, default encoding, or required permissions. The warning icon is present but not elaborated.

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, efficient sentence that front-loads the important warning symbol and key constraint. While brief, it avoids verbosity. However, the conciseness sacrifices necessary detail for parameter semantics and usage context.

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 high parameter count (9) and absence of output schema, the description is insufficiently complete. It does not explain return values, error conditions, or how default values work. The minimal coverage leaves significant gaps for the agent to interpret 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?

With 0% schema description coverage, the description must clarify parameters. It only explains that 'table' and 'query' are mutually exclusive. The remaining seven parameters (file_path, append, encoding, delimiter, always_quote, database_name, record_delimiter) are not mentioned, leaving the agent uninformed about their purpose and constraints.

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?

Tautological: description restates name/title.

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 instructs to provide exactly one of 'table' or 'query' and warns about absolute file paths. However, it omits guidance on when to choose this tool over export_json, export_xlsx, or import_csv, and does not mention the append or encoding options.

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?

Discloses file write capability and absolute path usage, and restricts queries to read-only types. However, does not mention default behavior for overwriting (append parameter exists but not described), leaving a gap in behavioral 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?

Single sentence with a warning emoji is concise and packs essential info. Could be slightly better structured with separate lines for constraints, but overall 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?

Despite mentioning table/query and file write, the description omits critical details: append behavior, encoding options, database_name context, and the exact file_path format. This is insufficient for a 6-param write tool with no 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?

With 0% schema description coverage, the description only adds meaning for table and query parameters. File_path is implied but not described in format or constraints. Append, encoding, and database_name are entirely unmentioned.

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?

Tautological: description restates name/title.

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?

Provides one key guideline: 'Provide exactly one of table or query.' However, no guidance on when to use this tool versus alternatives like export_csv or export_xlsx, nor when not to use it.

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 burden. It confirms safety, lists included schema objects, and mentions output formats. However, does not explain parameters (tables, database_name) or any side effects. Basic transparency but incomplete.

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?

Single sentence with clear structure, front-loaded with safety indicator and format options. Efficient but could include parameter hints without bloat.

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?

No output schema, no annotations, three optional parameters. Description covers main purpose and includes, but omits parameter details (tables filter, database selection) and error handling. Incomplete for full usage.

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%, so description must explain parameters. Only mentions format implicitly via SQL/JSON. Does not explain tables (filtering) or database_name parameters, leaving them undocumented.

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?

Tautological: description restates name/title.

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?

Includes 'SAFE' hint implying read-only usage, but lacks explicit when to use vs. alternatives like backup_database or import_schema. Does not specify prerequisites or conditions.

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 mentions file write capability and absolute paths (security concern) but lacks details on permissions, overwrite behavior, return value, or error conditions. Adequate but not thorough.

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 and front-loaded with a warning. However, it repeats the title verbatim, making it redundant. Every sentence is meaningful but could be more 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 complexity (5 parameters, 1 required) and lack of annotations or output schema, the description is insufficient. It omits details on return format, error handling, and interactions with sibling tools like import_xlsx.

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%, yet the description does not describe individual parameters. It only mentions table/query exclusivity and file_path being absolute. No info on sheet_name, database_name, or their constraints (max length, default). Minimal added value.

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?

Tautological: description restates name/title.

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 guidance: provide exactly one of table or query, and only read-only queries are allowed. It implies when to use this tool (for XLSX output) but does not contrast with alternatives like export_csv or export_json.

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 warns 'DESTRUCTIVE/SCHEMA CHANGE' and mentions table creation and coercion, but omits details like potential data loss, file accessibility requirements, or rollback behavior.

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 (one sentence) and front-loaded with a warning label. However, the warning and description could be separated for clarity, and the single sentence structure limits detail without being wasteful.

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 12 parameters, no output schema, and destructive nature, the description is incomplete. It misses prerequisites (e.g., database must be open), parameter roles, and error handling details beyond 'reports row-level errors'.

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 description only gives high-level behavior (headered CSV, table creation, coercion). It does not explain any of the 12 parameters (e.g., quote, escape, delimiter, fail_fast, coerce_types) which are critical for correct invocation.

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?

Tautological: description restates name/title.

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 usage for CSV imports but does not explicitly specify when to use vs alternatives (e.g., import_json for JSON files) or when not to use it (e.g., if table already exists without wanting DDL changes).

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 warns 'DESTRUCTIVE/SCHEMA CHANGE' and explains table creation from object keys and row-level error reporting. However, it omits behaviors like whether data is appended or replaced, and does not mention permissions or rollback.

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 sentence with a warning emoji, making it concise and front-loaded. However, the title and description are identical, introducing 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?

For a tool with 7 parameters, no output schema, and no annotations, the description is insufficient. It fails to explain return values, prerequisite conditions, or behavior when the table already exists.

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% schema description coverage, the description adds little parameter context. It hints at 'creates table' and error reporting but does not explicitly clarify parameters like fail_fast, batch_size, or create_table.

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?

Tautological: description restates name/title.

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 over alternatives, no prerequisites (e.g., file existence, JSON validity), no mention of when not to use it (e.g., table already exists).

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, description carries full burden. It prominently warns 'SCHEMA CHANGE', discloses creation of multiple object types, and states failure condition when objects exist without IF NOT EXISTS. This is good but could detail transactionality or permission requirements.

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?

Single sentence with no superfluous text. Front-loaded warning immediately signals importance. Every word earns its place despite lack of parameter detail.

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 no output schema and multiple sibling tools, description covers core function and failure case but omits return value, success indicators, and advanced behavior like rollback or partial failures. Adequate but not thorough.

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%, so description should compensate. It mentions 'SQL or JSON' as input formats but does not explicitly link to the 'format' parameter, nor describes 'schema' or 'database_name' parameters. Virtually no added value over schema structure.

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?

Tautological: description restates name/title.

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?

Provides context that tool fails if objects exist without IF NOT EXISTS, implying use for initial setup or migrations. However, no explicit guidance on when to use this over sibling tools like execute_schema_query or create_table, nor mentions prerequisites or recommended workflows.

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 discloses destructive schema changes, table creation when missing, and row-level error reporting, which are critical behaviors. However, it lacks details on data handling (e.g., append vs. replace for existing tables), progress feedback, or error format. With no annotations, more behavioral context is needed.

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 sentence with a warning emoji, making it concise and front-loaded with the most important cue ('DESTRUCTIVE/SCHEMA CHANGE'). However, it sacrifices necessary details, leaving significant gaps for a tool with 8 parameters.

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 8 parameters, no output schema, and no annotations, the description is profoundly incomplete. It does not explain key parameters (e.g., database_name, fail_fast, max_errors) or describe return values/error reporting format. Users/agents would need external documentation.

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 description only implicitly mentions header row handling via 'first row = headers', but none of the 8 parameters (e.g., batch_size, fail_fast, sheet_name) are explained. With 0% schema coverage, the description fails to add meaningful parameter guidance.

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?

Tautological: description restates name/title.

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 warns about destructive behavior and schema changes, implying caution, but does not provide explicit guidance on when to use this tool versus alternatives like import_csv, import_json, or import_schema. No when-to-use or when-not-to-use criteria are given.

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. It declares 'SAFE' (non-destructive), 'Max 100 results' (pagination), and 'Returns paths, sizes, dates' (output format). Could mention recursion, default directory, or errors.

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?

One concise sentence with a safety prefix, no wasted words. Front-loaded with 'SAFE' for quick assessment.

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 low complexity and no output schema, description covers what tool does, output, and limit. Lacks default directory behavior, but adequate for simple listing 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 coverage is 0% and only one optional parameter 'directory' with maxLength. Description implies it filters by directory but does not clarify default behavior when omitted or the exact meaning of the 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?

Tautological: description restates name/title.

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 includes 'SAFE' implying read-only, but no explicit when-to-use or alternatives. The agent can infer from sibling names that this is for finding database files, not for listing tables.

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 states it is 'SAFE' and supports pagination with a max limit of 1000, which adds behavioral context. However, with no annotations, it fails to disclose potential side effects, permission requirements, or idempotency details. It is partially transparent but not comprehensive.

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 short, front-loaded with the safety indicator, and uses two sentences. It is efficient but repeats the title exactly. No unnecessary words, but could be slightly more 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 four parameters, no output schema, and no annotations, the description covers the core purpose and pagination but omits database_name and the detailed verbosity output. It is adequate for a simple listing tool but not fully 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?

With 0% schema description coverage, the description must compensate. It explains verbosity values ('summary' for names only) and pagination implicitly, but does not clarify limit, offset, or database_name semantics. The value added beyond the schema is minimal.

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?

Tautological: description restates name/title.

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 a hint on using verbosity='summary' for names only, but lacks guidance on when to use this tool versus alternatives (e.g., describe_table, database_info). No when-not-to-use conditions or prerequisite context are given.

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?

Discloses that it sets the current context, returns database info, and errors if file not found. With no annotations, this provides sufficient behavioral context for a 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?

Single sentence, front-loaded with 'SAFE', no wasted words. Every part 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?

Provides key information: action, error case, result type. With one parameter and no output schema, the description is mostly complete, though could mention that it sets context for subsequent operations.

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?

Only parameter 'path' has schema constraints but no description. The tool description does not add any meaning about path format (absolute/relative, extension), leaving the agent without helpful guidance.

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?

Tautological: description restates name/title.

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 says 'use create_database to make a new one' for non-existent files, providing clear when-to-use guidance. However, no mention of when to use versus other tools like list_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?

Without annotations, the description discloses key behavioral effects: discarding all changes and restoring previous state. However, it omits details like whether an active transaction is required or the irreversible nature of the rollback.

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 very short and front-loaded with a warning emoji, but it lacks essential details about parameters and usage context, making it too terse for effective use.

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 has one parameter with no schema description and no output schema, the description should explain the parameter and usage more thoroughly. It fails to do so, leaving significant gaps for the agent.

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 one parameter (database_name) with 0% coverage, yet the description does not mention this parameter at all, leaving the agent without guidance on what to provide or whether it's 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?

Tautological: description restates name/title.

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 usage when wanting to discard changes, but does not explicitly state when to use it versus alternatives like commit_transaction, nor does it mention prerequisites such as an active transaction.

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 must disclose behavioral traits. It mentions reclaiming space and defragmenting, which implies a write operation, and states the free space requirement. However, it omits details like locking behavior, duration, or failure conditions.

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, but the first sentence repeats the title verbatim. The second adds a requirement. Could be more concise by removing redundancy and front-loading the critical space requirement.

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 maintenance nature of this tool, the description lacks information on side effects (e.g., database unavailability), return values, or scenarios where vacuuming is inappropriate. With no output schema and no annotations, more contextual details are needed.

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%, and the description does not explain the optional parameter 'database_name' beyond its name in the schema. It lacks details on what happens if omitted (e.g., defaults to current database) or formatting constraints.

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?

Tautological: description restates name/title.

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 provides a key precondition: 'Requires free space equal to database size.' This helps the agent decide when to use it. However, it does not mention when not to use it or suggest alternatives.

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