Tokenectomy-Razor

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

With no annotations, the description fully discloses side effects (None, read-only), auth requirements (None required, offline), rate limits (1MB, 128 depth, 50k node visits), return shape (JSON with language, findings_count, duration_ms, findings array), and failure modes (empty findings, error on unsupported language or exceeded limits). This is comprehensive and leaves nothing ambiguous.

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 long but tightly organized in bullet points with clear headers. Every sentence adds value: side effects, auth, rate limits, return shape, failure modes, when/when-not, and prerequisites are all addressed. It front-loads the core purpose and then details specifics without 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?

This is a complex tool (static analysis, multiple detection categories, limits, error conditions) with no annotations or output schema. The description fully compensates by specifying the exact return structure, failure modes, prerequisites (supported languages), and constraints. An agent has everything needed to call it 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 input schema already offers 100% description coverage for both parameters, including constraints (size limit, case-insensitivity, supported values). The description adds little new meaning for parameters beyond what the schema provides; it reiterates the 1MB limit but that's behavioral context rather than parameter semantics. Baseline 3 applies because the schema does the heavy lifting.

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 the verb 'Performs static AST code analysis using Tree-sitter' and the resource 'code', and specifies the exact detection categories (resource leaks, security vulnerabilities, logic flaws). It names alternatives in the 'When NOT to use' section (get_error_context, apply_code_patch), distinguishing this tool from siblings clearly.

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 a dedicated 'When to use' section recommending proactive use before commits or for Python file review, and a 'When NOT to use' section explicitly naming two sibling tools (get_error_context and apply_code_patch) with conditions for each. This is explicit routing guidance.

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

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

With no annotations provided, the description carries the full burden and covers it comprehensively: side effects, permissions, rate limits, return shape, rollback behavior, and failure modes. It explicitly states that the file is overwritten on success, restored on failure, and that path traversal is blocked. This is far beyond the typical threshold.

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 with clear sections (side effects, auth, rate limits, return shape, failure modes, usage, prerequisites) and front-loads the core function. It is slightly redundant—syntax validation and rollback are stated both in the opening sentence and in side effects/failure modes—but every section otherwise 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?

For a mutation tool with 4 parameters, no annotations, and no output schema, the description is complete: it explains side effects, permissions, rate limits, return shape, failure modes, prerequisites, and when to use it. Nothing an agent needs to invoke this tool safely and correctly is missing. The return shape section compensates for the absent 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 100%, so the baseline is 3, and the description does not add parameter-specific detail beyond the schema. It repeats some constraints already in the schema (exact match, syntax/indentation), so the description adds no meaningful new parameter semantics, but the schema itself is already rich.

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 opens with a specific verb ('Applies') tied to a resource ('atomic, verified code edit to a specific file') and a clear mechanism (substituting original_code with new_code). It also names distinct behaviors like automatic syntax validation and rollback, which separates it from siblings focused on analysis or context retrieval.

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 explicit 'When to use' and 'When NOT to use' sections, with conditions and an alternative ('use get_error_context first'). It clearly states when the tool is appropriate (finalized fix needing safe transactional application) and when it is not (speculative edits, whole-file generation), leaving no ambiguity.

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 side effects are none, it is read-only in-memory evaluation, requires no auth, has no rate limits, and details the exact return shape including fields and possible health grade values.

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 structured with bullet points and front-loads the core purpose. Each section adds distinct value: side effects, auth, rate limits, return shape, when to use, and when not to use. Nothing feels redundant.

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 one parameter, no output schema, and no annotations, the description fully compensates: it explains input expectations, return format, safety profile, and usage boundaries. An agent has everything needed 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?

Schema coverage is 100% and the parameter description already explains that payload is a raw string, stack trace, or prompt payload. The tool description adds mild extra context about error logs and code snippets but does not fundamentally expand parameter semantics beyond the schema.

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

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

The description clearly states the tool audits raw error logs, code snippets, or prompt payloads for token bloat, framework noise, and credential leaks. It differentiates itself from siblings by explicitly saying it does not apply file edits or query Stack Overflow.

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 explicit when-to-use guidance: proactively for large terminal dumps or before sending long logs to an LLM. It also gives clear when-not-to-use guidance, naming apply_code_patch and search_stack_overflow as 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 zero annotations provided, the description carries the full burden and discharges it completely: it declares no side effects (read-only, no workspace/git/env mutation), no auth required, no rate limits (local execution), the JSON return shape with field-level detail, and concrete failure modes (missing source files → omitted snippets with sanitized trace still returned; unreadable input → error JSON). It also lists prerequisites. Nothing about actual behavior is left to inference.

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 definition is long but every bullet earns its place: purpose sentence up front, then tightly grouped bullets for side effects, auth, rate limits, return shape, failure modes, usage routing, and prerequisites. Since annotations and output schema are both absent, this length is justified rather than padded — each section answers a distinct question an agent would have before invoking.

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 having no annotations and no output schema, the description covers every category an agent needs: purpose, when/when-not with alternatives, behavioral safety profile, exact return structure (including nullable git_diff), failure modes, and prerequisites. A tool with 3 parameters, one enum, and nuanced output is fully specified for correct invocation with no unresolved questions.

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

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

Schema description coverage is 100%, so per the rubric the baseline is 3. The schema's own descriptions are thorough — log includes format/size/sanitization semantics, strategy explains each enum value with its default, and context_lines gives range, default, and token tradeoff. The description's Return Shape section adds light contextual interplay (strategy affects output) but doesn't need to compensate for any schema gap.

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?

Opens with a specific verb-and-resource statement: 'Extracts focused source code snippets and git diffs from a raw error log or stack trace.' The scope is precise (error logs/traces only, noise stripped, credentials redacted), and the 'When NOT to use' section names each sibling tool with its distinct purpose, so an agent can unambiguously tell this apart from search_stack_overflow, apply_code_patch, and analyze_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?

Explicit 'When to use' states the exact trigger conditions: 'Call immediately when receiving a runtime exception, test failure, or compiler error.' The 'When NOT to use' section gives exclusion criteria AND names the correct alternative for each (web search → search_stack_overflow, file modification → apply_code_patch, linting clean code → analyze_code). This is the gold standard for routing guidance.

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

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

With no annotations provided, the description carries the full burden and covers side effects (strictly read-only), auth requirements (no API key), rate limits, return shape, and failure modes. This is precisely the behavioral context an agent needs before invoking an external network 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 front-loaded with the core purpose and then organized into clearly labeled bullet sections. Every bullet conveys necessary operational guidance, and there is no filler or redundant restatement of the tool name.

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

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

Given that there is no output schema and the tool depends on external network behavior, the description fully covers return shape, failure modes, rate limits, and prerequisites. An agent has all the information needed to decide whether and how to call this tool safely and 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 already documents the query parameter at 100% coverage, so the baseline is 3. The description adds valuable semantics beyond the schema by advising that the query must be free of project-specific paths/tokens and recommending a 3-150 character length, which helps the agent formulate a valid and safe query.

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 states a specific verb and resource: 'Queries the public Stack Overflow / Stack Exchange API' for solutions matching an error signature. It also differentiates from siblings by referencing local context tools and code-editing tools, so an agent can clearly tell what this tool is for.

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 explicit 'When to use' and 'When NOT to use' sections naming sibling tools get_error_context and apply_code_patch as alternatives. It specifies the conditions under which this tool is preferred and when it must be avoided, leaving no room for inference.

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