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

The description details key behaviors: sequential processing per file, default dry_run to prevent writes, capping of large match sets via OLLAMA_MCP_MAX_BATCH_FILES, and the need to set dry_run=False to apply changes. No annotations are provided, but the description fully compensates.

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 paragraph that front-loads the main purpose and then explains parameters and behavior. It is reasonably concise, though a bullet list could improve scanability.

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 output schema exists and the description covers purpose, parameters, safety (dry run), limitations (capping), and procedural details, the description is complete enough for an agent to select and invoke the 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?

With 0% schema description coverage, the description is essential. It explains glob_pattern as matching relative paths under root_dir, root_dir's default behavior, dry_run's default value, and that instruction is the refactor directive. All parameters are effectively documented.

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 specific action ('Apply a refactor instruction') and the resource ('every file matching a glob pattern, sequentially'). It distinguishes from sibling tools like refactor_code, which likely targets single files.

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

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

The description explains that the tool is for sequential refactoring across multiple files matching a glob pattern, with dry_run defaulting to true for safety. It mentions the environment variable cap but does not explicitly list when not to use or alternative tools.

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 only states it 'reviews a diff as if for a pull request' but does not disclose whether it is read-only, if it requires authentication, or what happens if both diff and diff_file are provided (schema allows both as optional). Missing behavioral traits.

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, straight to the point, with no extraneous information. Every sentence adds value: first defines the tool, second gives parameter 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?

Given 4 parameters, 0% schema coverage, and no annotations, the description partially covers parameter semantics but omits one parameter ('think'). It does not need to explain return values because an output schema exists. Still, the omission and lack of constraints leave it somewhat 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%, so the description must compensate. It explains 'diff' as inline diff text, 'diff_file' as a server-side path, and 'context' as PR description. However, it fails to explain the 'think' parameter, leaving that 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?

The description clearly states 'Review a git diff... as if for a pull request.' This is a specific verb (review) and resource (git diff), and it distinguishes from sibling tools like 'explain_code' or 'review_code' by focusing specifically on diffs.

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 'Provide exactly one of diff or diff_file' and explains the role of 'context'. It provides clear guidance on parameter usage, though it does not explicitly mention when not to use this tool or compare with alternatives.

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 mentions that explanations are usually fast, implying low latency, but does not disclose other behavioral traits like access to file system, error handling, or rate limits. The output schema exists, so return format disclosure is not required.

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

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

The description is extremely concise, with two clear sentences. The first front-loads the purpose, and the second provides critical usage guidance. No unnecessary 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 tool has 3 parameters (0 required) and an output schema, the description covers purpose, parameter usage, and a hint about performance. It could mention what happens if neither code nor file_path is provided, but overall it's sufficiently complete for its complexity.

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 meaningfully explains that code and file_path are mutually exclusive and that think=False is usually sufficient. This adds significant clarity beyond the schema's defaults, though it could detail accepted formats for code or file_path.

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 explains code, including control/data flow and non-obvious behavior. It specifies the action (explain) and resource (code), and implicitly distinguishes from sibling tools like review_code or fix_code.

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

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

The description provides explicit guidance to provide exactly one of code or file_path, and suggests that think=False is usually sufficient. However, it does not explicitly state when not to use this tool versus alternatives, though the purpose alone provides some differentiation.

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 exist, so the description must disclose behavior. It implies fixing a bug (mutation) but does not specify whether the tool modifies the original code, returns a diff, or requires permissions. The output schema exists but is unused in the description.

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

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

Two short, focused sentences with no redundant information. The first states purpose, the second gives constraints and tips.

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 4 parameters and no annotations, the description covers parameter usage but lacks information on return format, side effects, and behavioral details. An output schema exists but is not leveraged.

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 explains the mutual exclusivity of 'code' and 'file_path' and the value of 'error_message', adding meaning to the 0% schema coverage for parameters. However, 'think' is not described.

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 verb 'Diagnose and fix a bug' and the resource 'code', distinguishing it from sibling tools like generate_code (creation) or explain_code (explanation).

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 explicitly states to provide exactly one of 'code' or 'file_path' and to include 'error_message' when available, giving clear usage guidance. However, it does not directly compare with sibling tools.

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?

Mentions use of local Ollama model and server-side path for context_file, but does not disclose important behavioral traits such as file creation, network calls, or model limitations. No annotations present to supplement.

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?

Every sentence is purposeful and provides actionable guidance. Information is front-loaded, with efficient use of 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?

Covers key parameter usage but omits output mechanism (e.g., where generated code is returned or saved). Output schema exists but description does not mention it, leaving the return format unclear.

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?

Adds meaning to 'think' (speed vs completeness) and 'context_file' (server-side path for context), but does not explain 'language' parameter at all, leaving it ambiguous despite being optional.

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 explicitly states it generates new code from natural-language instructions using a local Ollama model, differentiating it from sibling tools like 'review_code' or 'fix_code' which operate on existing code.

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 clear advice on when to set 'think' to False vs True and how to use 'context_file' to preserve context window, but does not compare with sibling tools to guide selection.

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

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

With no annotations, the description carries full burden. It discloses that the tool checks connectivity and reports available models, and mentions it confirms a model is 'reachable and pulled'. A slight gap: it doesn't specify whether it tests anything beyond basic reachability or what 'available' means, but it's largely transparent.

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

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

Two concise sentences: first states purpose, second provides usage context. Every word earns its place with no redundancy.

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

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

Given the tool's low complexity (no params, simple health check), the description is fully complete. The existence of an output schema covers return values, and the description covers connectivity and model availability.

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

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

The tool has zero parameters, and schema description coverage is 100% (trivially). The description adds no parameter info, but none is needed. Baseline score of 4 is appropriate.

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 ('Check connectivity') and resource ('Ollama host') and clearly states the output ('report available models'). It distinguishes itself from sibling tools which are all code-related 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?

Explicitly advises to call this tool first if other tools fail or proactively before delegated work, providing clear when-to-use guidance. It implies the tool is for diagnostics and readiness checks.

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 discloses that the tool returns full refactored code plus a summary, does not write files, and preserves external behavior. However, it does not mention handling of invalid inputs or permissions for file_path.

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

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

Two concise sentences that front-load the purpose, then provide usage rules and an alternative tool. 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 no annotations and output schema present, the description covers purpose, usage, behavior, and return type adequately. However, the undocumented 'think' parameter is a gap for 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?

Schema description coverage is 0%, so description must compensate. It explains that 'code' and 'file_path' are mutually exclusive and describes 'instruction', but does not document the 'think' parameter. Partial coverage but misses one 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?

The description clearly states the tool refactors code based on an instruction while preserving external behavior. It distinguishes itself from sibling tools like batch_refactor by noting that it does not write files.

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

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

Explicitly states to provide exactly one of 'code' or 'file_path', and provides an alternative tool (batch_refactor) for applying changes to disk. This gives clear context on when to use this tool vs alternatives.

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 explains that `file_path` is a server-side path read directly by the tool, indicating no side effects. It also mentions 'saving your context window,' adding useful behavioral context. However, it does not explicitly state read-only or disclose any potential consequences.

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 purpose, and each sentence adds value. No redundant or unnecessary text.

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 (4 params, no required, no enums, has output schema), the description covers the essential input selection and purpose. With an output schema present, it does not need to detail return values. It is complete enough for an AI agent to use 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?

Schema description coverage is 0%, so the description must compensate. It explains `code` (inline text), `file_path` (server-side path), and `focus` (e.g., 'concurrency' or 'input validation'). The guideline to provide exactly one of code/file_path adds value. However, the `think` parameter (boolean, default true) is not explained, but it is likely internal.

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

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

Description clearly states 'Review code for correctness bugs, security issues, and simplification opportunities.' The verb 'review' and resource 'code' are specific, and listing the aspects distinguishes it from siblings like fix_code (fixing) and explain_code (explaining).

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 clear guidance on input selection: 'Provide exactly one of `code` or `file_path`' and explains that `focus` can narrow the review. However, it does not explicitly state when not to use this tool or compare to siblings like code_review_diff or explain_code, though the context is implied.

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 describes input handling but omits behavioral traits such as whether tests are appended or overwritten, permissions needed, or side effects. Transparency is limited.

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

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

Three sentences, front-loaded with purpose, no superfluous words. Efficient and well-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 4 parameters, no annotations, and an output schema that is not described, the description covers usage but lacks detail on return values, error handling, and the 'think' parameter. Adequate but with 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 coverage is 0%, so description must compensate. It explains the mutual exclusivity of code and file_path and hints at framework inference, but does not mention the 'think' parameter. Adds moderate value but not full 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?

Description clearly states the tool writes tests covering golden path and realistic edge cases, with a specific verb and resource. It distinguishes from sibling tools that focus on refactoring, reviewing, or explaining code.

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?

Description gives clear input constraints (exactly one of code or file_path) and hints at framework selection, but does not explicitly state when not to use or list alternatives. Context is clear but lacks exclusions.

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