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

With no annotations provided, the description carries the full burden of behavioral transparency. It thoroughly discloses the cache's scope (keyed by file path), lifetime (server process), and the effect of clearing it (next calls re-read from disk). It also clarifies the tool's side effects (invalidates cache, does not modify config files). No contradictions with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured, beginning with a clear one-sentence summary followed by a concise paragraph linking the cache behavior to practical implications. Every sentence adds value, and the information is front-loaded for quick scanning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a zero-parameter, side-effect-free (non-destructive) utility tool, the description fully covers what the tool does, when to use it, and what to expect. The presence of an output schema is irrelevant here, but the description does not need to mention return values given the output schema exists. The description is completely adequate for an agent to know exactly when and how to invoke it.

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 baseline of 4 applies. The schema is trivially complete, and the description adds no parameter documentation because none is needed. However, the description's emphasis on 'no arguments required' is implicit, which is acceptable.

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 function: 'Clear SQLFluff's internal config-file cache.' It uses a specific verb ('Clear'), identifies the resource ('SQLFluff's internal config-file cache'), and differentiates itself from sibling tools like lint_file and fix_file by explaining that it handles cache invalidation, not 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 explicitly states when to use the tool: 'Call this tool after editing any SQLFluff config file to force the next lint_file / fix_file / parse_file call to re-read it from disk.' It also explains the underlying problem (caching) and the consequence of not using it (stale results), giving clear contextual guidance without needing 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 carries the behavioral burden and does so by explaining the write flag: overwriting in place when True, and returning fixed SQL without touching the file when False. It also notes config layering behavior, though it omits error/permission details.

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, and uses a clear Args list. Every sentence adds useful information with no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple 3-parameter tool and presence of an output schema, the description covers purpose, side effects, and parameter behavior completely. It does not need to restate return values thanks to 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?

Schema description coverage is 0%, but the Args block fully explains path, write semantics, and config_path layering. This adds meaning beyond the bare schema and compensates for the lack of structured 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?

The opening line 'Fix a SQL file on disk' uses a specific verb and resource, immediately clarifying the tool's function. It also distinguishes from sibling fix_sql by scoping to files, and mentions config honoring.

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 clearly implies file-based usage via 'on disk' and the path parameter, giving context for when to choose this over SQL-string tools. It does not explicitly name alternatives or exclusions, but the file scope is unambiguous.

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

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

With no annotations, the description carries the burden. It discloses that it returns the fixed SQL text, does not touch any file, and requires an explicitly specified dialect. It lacks details on error handling or side effects, but these are minimal for a pure string transformation.

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 the purpose, followed by a compact Args section. Every sentence adds value, 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?

The tool is simple (fix SQL string), and the description covers its purpose, parameters, return value, and safety property ('does not touch any file'). Although an output schema exists, the description already states the return type, making it 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 description coverage is 0%, but the description fully compensates by explaining each parameter: 'sql' as text to fix, 'dialect' with concrete SQLFluff examples, and 'rules' as optional restrictions. This adds 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 the action: 'Fix a raw SQL string using an explicitly specified dialect and return the fixed SQL text'. It also explicitly notes 'does not touch any file', distinguishing it from file-based siblings like fix_file.

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 this tool (for raw SQL strings) and, via the parenthetical 'does not touch any file', distinguishes it from file-based tools. It does not explicitly name alternatives or state exclusions, but the scope is clear.

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 present, so the description carries the full burden. It discloses config walking and layering behavior, which is useful context. Yet it does not explicitly state whether the operation is read-only or what happens on error, leaving some ambiguity about safety and outcomes.

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, front-loaded with the core purpose, and includes a clean Args section. Every sentence adds value with no fluff, and the structure is easy to scan.

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 is simple (2 parameters, no nested objects), and an output schema exists, so return values don't need to be in the description. The description covers config discovery and parameter semantics well. The only minor gap is the lack of an explicit statement about side effects, but 'lint' generally implies non-destructive.

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 provides only bare titles with no descriptions, leaving the Args section in the description to carry all parameter semantics. It fully explains both path and optional config_path, including layering behavior, which is more than the schema offers.

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 action (lint), the resource (SQL file on disk), and adds scope by mentioning config discovery. The phrase 'on disk' differentiates from sibling tools like lint_sql, which likely lints SQL strings.

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 linting files on disk and explains config discovery, providing clear context. However, it does not explicitly name alternatives or state when not to use this tool, though the 'on disk' phrasing naturally separates it from string-based linting.

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?

There are no annotations, so the description carries the full burden of explaining behavior. 'Lint' implies a read-only analysis, but the description does not explicitly state it will not modify anything or what the return value looks like. However, the presence of an output schema mitigates the need to describe return values, and the tool's nature as a linter makes destructive side effects unlikely.

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 opens with a clear, direct one-line purpose, then efficiently breaks down parameters in a structured Args block. Every sentence and piece of documentation adds value—no fluff, no repetition of schema titles. This is an model of concise, scannable tool documentation.

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 complexity (3 parameters, no annotations), the description covers all necessary aspects: what it does, how to use each parameter, and where to find valid dialect values. Since an output schema exists, the lack of return-value explanation is acceptable. The description is complete enough for an agent to select and invoke this tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema has 0% description coverage, so the description must fully document parameters. It does so comprehensively: 'sql' is defined as the SQL text to lint, 'dialect' includes concrete examples and a pointer to list_dialects(), and 'rules' explains its optional filtering purpose. This adds real 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 the action ('Lint') and the resource ('a raw SQL string'), and adds a crucial differentiator: it uses an explicitly specified dialect. This distinguishes it from sibling tools like lint_file (which handles files) and fix_sql (which fixes rather than lints).

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 this tool: when you have a raw SQL string and need to specify a dialect. It does not explicitly mention alternatives or exclusions, but the phrase 'raw SQL string' strongly signals the file-based alternative (lint_file). The dialect reference to list_dialects is also a clear instruction for usage.

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 clearly states the read-only listing behavior and the subject matter (supported SQL dialects). It does not detail output format or ordering, but for a simple enumeration tool this is acceptable and not misleading.

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 with no filler. It efficiently states what the tool does and its intended companion tools, every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With zero parameters, an output schema present, and low complexity, the description fully covers the tool's purpose and usage context. It doesn't need to explain return values because the output schema exists, and there are no potential user-input pitfalls to warn about.

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 zero properties, so there are no parameters to describe. The baseline of 4 applies because the schema coverage is complete and the description adds relevant context about the tool's purpose, even though no param details are needed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses the specific verb 'List' and clearly names the resource ('SQL dialects SQLFluff supports'). It distinguishes the tool from sibling tools like lint_sql or fix_sql, which are operations on specific SQL content rather than meta-information.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly says 'for use with lint_sql / fix_sql / parse_sql', providing clear usage context as a prerequisite for those tools. It does not mention when not to use it or alternative tools, but given there are no other listing tools, the context is sufficient.

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 the full behavioral disclosure burden. It transparently discloses config discovery behavior ('honoring discovered .sqlfluff config') and how config_path layers on top, which adds value. However, it does not mention side effects (though parse implies read-only) or error behavior, so it is adequate but not highly detailed.

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: a one-line purpose statement followed by a compact Args list. No redundant or filler sentences—every word contributes to understanding the tool's function and 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 the tool's simplicity and the presence of an output schema, the description covers the essential context: file parsing, config honoring, and parameter semantics. It does not explicitly mention how this differs from parse_sql, but that is not required for using the tool correctly. The description is complete for its scope.

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 compensates by providing an Args section explaining both parameters: path is the file to parse, and config_path is an optional extra config file layered on discovered config. This adds meaning beyond the schema's plain type/title fields, though examples or edge cases are not included.

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 function: 'Parse a SQL file on disk and return its parse tree.' The verb 'parse' and resource 'SQL file on disk' are specific, and the phrase 'on disk' distinguishes it from sibling parse_sql, which likely parses SQL strings.

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 file-based parsing ('file on disk') and mentions honoring .sqlfluff config, but it does not explicitly contrast with alternatives like parse_sql or state when not to use this tool. The context is clear, but no explicit when-to-use or exclusion is 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 are provided, so the description must carry the full burden of behavioral disclosure. It states the operation (parse and return tree) but does not mention side effects, error behavior, or non-destructive guarantees. The agent is left to infer safety and failure modes.

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 clear sentence followed by a compact Args list. Each word earns its place, and the primary purpose is front-loaded without unnecessary 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?

For a simple 2-parameter tool with an output schema, the description adequately covers the core operation and parameters. It lacks usage alternatives and error behavior, but these are addressed in other dimensions, and the output schema obviates the need to describe 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?

The schema has 0% description coverage with only titles 'Sql' and 'Dialect'. The description adds full meaning: 'The SQL text to parse' and 'SQLFluff dialect name, e.g. ...' with example values, which is essential 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?

The description uses a specific verb 'Parse' with a resource 'raw SQL string' and explicitly states it returns a parse tree. It clearly distinguishes from siblings like parse_file and lint_sql by emphasizing the raw string input and required dialect.

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 raw SQL strings and requires an explicit dialect, but does not mention alternatives or when not to use. Sibling names like parse_file hint at a file-vs-string contrast, but the description itself provides no explicit guidance.

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