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

Clearly describes it returns a verdict, canonical form, and suggestions. With no annotations, the description carries full burden and does so adequately, though it could explicitly state no side effects.

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 sentences with examples and usage context—no wasted words. Front-loaded with purpose.

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 purpose, examples, usage guidance, and return type. Without output schema, the description of the verdict is slightly vague but 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?

Schema coverage is 100%, and the description adds an example but no additional semantics beyond the schema's description of 'identifier'. Baseline 3 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 clearly states the tool checks identifier naming conventions with specific examples ('n_dims' vs 'ndim'), distinguishing it from siblings like 'suggest_name' or 'list_conventions'.

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 before committing new code or when reviewing identifier names', providing good context. However, it does not mention when not to use or list 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 must fully disclose behavior. It explains that the tool combines function body, structural summary, domain concepts, and logic cluster, but does not detail how it handles large scopes, truncation, or errors. The description is adequate but lacks edge-case 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?

The description is a concise two sentences: first sentence defines the purpose and output, second gives usage contexts. Every phrase earns its place, and the action verb 'Assemble' is front-loaded.

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 two parameters with full schema coverage and no output schema, the description explains the tool's purpose, components, and usage. It does not mention output format or limitations, but for a text assembly tool, it is sufficiently complete.

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

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

Schema coverage is 100%, and the description merely restates the parameter descriptions from the schema (scope as concept/entity/file path, max_tokens as token budget with default). It adds no new meaning beyond what the schema already provides.

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 that the tool assembles a token-efficient context for a concept, entity, or file, combining multiple aspects. It is clear what it does, but it does not explicitly differentiate from siblings like describe_file or concept_map, which also provide summaries.

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 use cases: assembling context for another LLM, when asked to summarize compactly, or building prompts. However, it does not mention when not to use this tool or suggest alternative tools among the listed siblings.

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

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

With no annotations, the description carries full burden. It discloses behavioral traits effectively: it provides a layout overview with counts and density, implying a read-only operation. It lacks explicit safety or performance details but adds value beyond the empty schema.

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 sentences with no wasted words. The first sentence front-loads the core purpose and outputs, and the second provides usage context. Every sentence 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 zero-parameter tool with no output schema, the description is fairly complete: it explains what it does and when to use it. It could add detail about the output format, but it's adequate for an agent to select and invoke 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 has zero parameters, so schema_description_coverage is 100%. The description does not need to add parameter info, and it doesn't. Baseline score of 3 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 clearly states the tool shows 'semantic topology of the codebase' with specific outputs like directories, entity counts, and concept density. It uses a specific verb 'shows' and resource, distinguishing it from sibling tools like list_concepts or query_concept by positioning it as an initial overview tool.

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 'Use as a first call to understand codebase layout before drilling into specific concepts or symbols.' This provides clear when-to-use guidance and implies alternatives (drilling tools) without naming them explicitly, which is sufficient for an agent.

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 the description carries the full burden. It correctly discloses that the tool does not read file content, accepts partial paths, and returns annotated symbols. It could mention that it is read-only and safe, but the description is clear enough.

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 the core purpose, no redundancy. Every sentence serves a clear function: purpose, usage guidance, and parameter behavior.

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 a single parameter, no output schema, and no annotations, the description covers all necessary information: what the tool does, when to use it, how parameters work, and what the return structure looks like. It is complete for an AI agent to invoke 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%, so baseline is 3. The description adds value by explaining that partial paths are accepted and giving an example ('networks.py' matches 'src/networks.py'), which is not in the schema description.

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 specifies the verb 'Describe', the resource 'file's structure', and distinguishes it from siblings like 'describe_symbol' by emphasizing it does not read the file. It clearly states what it returns: classes, functions, methods annotated with domain concepts.

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 it ('when you need to understand a file's shape'), and provides an alternative tool ('Use describe_symbol to drill into any symbol shown'). This directly helps the agent decide between 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?

No annotations are provided, so the description carries full burden. It discloses the returned data (raw function body, cluster membership, centrality). It lacks details on side effects, permissions, error handling, or size limits. Overall adequate 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 two sentences with no redundant information. The first sentence states the core purpose and outputs, the second provides usage examples. Extremely concise 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?

For a simple tool with one parameter and no output schema, the description fully explains what the tool returns and gives sample queries. No further clarification is needed for correct 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 description coverage is 100% for the single parameter 'name', which has a clear description. The tool description does not add additional semantics beyond the schema, so baseline 3 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 explicitly states the tool 'Describe the behavioral logic of a function or class' and lists the specific returns (raw function body, logic cluster membership, structural centrality). It distinguishes from siblings like describe_symbol or describe_file by focusing on internal logic and dependencies.

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 usage cues: 'Use when asked "what does this function do internally"...' This clearly indicates when to invoke. However, it does not mention when not to use or alternative tools for similar queries.

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 it returns signature, parameters, callers, callees, and domain concepts without reading source. No destructive hints, but could mention if it has any side effects or requires permissions.

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 sentences, each adding value: first defines action and output, second gives usage pattern and comparison. No redundant 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?

For a single-parameter tool with no output schema, the description thoroughly covers what it does, when to use it, and what it returns. Sibling tools are distinct.

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%, so baseline is 3. The description adds no extra parameter info beyond the schema's 'Function or class name' description.

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

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

The description clearly states the tool's purpose: 'Describe a function or class WITHOUT reading its source file' and lists return values. It distinguishes from siblings like 'Read' by emphasizing it is faster and more informative.

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 usage guidance: 'Use when asked what does function X do or what is class X.' Also contrasts with alternative (Read) 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?

No annotations provided, but description effectively explains non-destructive export behavior and output nature. Does not mention potential size or scope limitations, but overall transparent given zero parameters.

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 concise sentences: first defines action/content, second provides usage guidance, third describes output utility. No redundant or missing information.

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, but description sufficiently explains the YAML pack output and its contents. With zero parameters, the description covers all necessary context for an agent to use 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?

Tool has no parameters, and schema coverage is 100% (empty). Description adds no further parameter info, which is acceptable as baseline for zero-parameter tools.

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

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

Clearly states it exports full domain knowledge as a portable YAML pack, listing specific contents (abbreviations, conventions, terms, associations) and use cases. Distinguishes from sibling tools like list_concepts or list_conventions by being a comprehensive export.

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 defines when to use with phrases like 'export conventions', 'create a domain pack', 'share naming rules'. Lacks direct comparison to alternative tools or when not to use, but trigger phrases are 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 provided, so the description must cover Behavioral traits. It explains the method (logic embeddings) and what is returned (similarity scores), but doesn't explicitly state it's read-only or mention any side effects or permissions.

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 sentences plus a list of example queries. No unnecessary words, front-loaded purpose, very 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 no output schema, the description briefly mentions returns similarity scores but does not describe the result structure, leaving some ambiguity for an 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?

Schema coverage is 100%, so the schema already describes both parameters. The description does not add additional parameter-level details beyond what the schema provides, meeting the baseline.

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

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

The description clearly states it finds entities with similar behavioral patterns using logic embeddings, and explicitly distinguishes from naming-based similarity. It gives concrete query examples.

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 natural language triggers like 'what other functions do the same thing' and clarifies it ignores naming, which effectively guides an agent on when 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?

Discloses it returns a ranked list of concept names, implying a read operation. No annotations provided, but description adequately conveys its non-destructive nature and output format.

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 sentences, front-loaded with purpose, no redundancy, efficiently conveys all necessary information.

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 output (ranked list of concept names), usage context, and relationship to siblings. Given no output schema, it explains return values adequately. Could mention default behavior for top_k, but overall 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 describes the one optional parameter (top_k) as maximum number of concepts to return. Tool description does not add extra context beyond schema, but schema coverage is 100% so baseline 3 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 clearly states the tool lists the project's domain vocabulary ranked by importance, providing a semantic overview. It distinguishes from sibling tools like query_concept and locate_concept for drilling down.

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 tells when to use the tool: when asked about project's main concepts or orienting in an unfamiliar codebase. Also guides to use query_concept or locate_concept for further exploration.

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 must carry burden. It discloses that conventions are detected from code and provides real examples, but does not state read-only nature or side effects. Adequate 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?

Two sentences: first describes outputs, second provides usage guidance. No filler, front-loaded with key information.

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 parameters or output schema, description covers what is returned (patterns and examples) and when to use. Could benefit from mentioning return structure, but adequate for the tool's simplicity.

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?

No parameters; schema coverage is trivially 100%. Baseline for 0 params is 4. Description adds value by explaining the tool's return content, so score holds at 4.

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 specifies the verb 'list' and resource 'naming conventions', detailing prefix, suffix, conversion, and casing patterns with examples. It clearly distinguishes from sibling check_naming by focusing on an overview.

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 when to use: when asked about coding style, before writing new code, or when onboarding. Does not mention alternatives or when not to use, but context 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 provided, so the description carries the burden. It implies a read-only query operation through examples and purpose, but does not explicitly state non-destructiveness or other behavioral traits. Still, the intent is clear and no contradictions exist.

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

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

The description is concise with two main sentences plus usage examples. It is front-loaded with the core purpose, and every sentence contributes value. 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 no output schema, the description mentions return of 'entity names with their domain concept tags', which is adequate but could specify format or pagination. It is fairly complete for a list tool, with enough context to guide 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?

Schema description coverage is 100%, so baseline is 3. The description adds example values for 'concept' but does not elaborate on 'role' or 'top_k' beyond what the schema already provides. It adds mild context but no substantial new meaning.

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 finds classes and functions matching a concept, with examples like 'loss functions' and 'network architectures'. It directly addresses the intent of listing entities by concept and distinguishes from the sibling 'describe_symbol' by mentioning drilling down.

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 usage scenarios with example queries ('what loss functions exist', 'list all X') and contrasts with grep, explaining when this tool is superior. It also directs users to 'describe_symbol' for further details, setting clear boundaries.

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, but description implies a read-only operation that ranks results. It does not disclose potential side effects, rate limits, or response structure beyond the shortlist. Adequate but could explicitly state it's non-destructive.

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 sentences, no redundant information. First sentence defines function and output, second gives use cases. 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?

For a simple tool with one parameter and no output schema, the description is complete: it explains purpose, typical use cases, and the nature of the result (ranked shortlist). No 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?

The single parameter 'term' is fully described in the schema, and the description adds context (e.g., 'e.g. 'transform''). The description explains how the parameter is used to find entry points, adding meaning 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?

The description clearly states the tool finds best entry points for understanding a concept, returning a ranked shortlist of key functions, classes, and files, plus contrastive concepts. It distinguishes from sibling tools like 'trace_concept' by focusing on initial exploration.

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 use cases ('how does X work', 'where should I look for X'), giving clear context for when to invoke. Lacks explicit guidance on when not to use or direct alternatives, but the specificity is strong.

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 bears full transparency responsibility. It only mentions comparing revisions and showing changes, but does not disclose prerequisites (e.g., git availability), performance, or output format. Minimal behavioral insight.

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 consists of two sentences, with the primary action front-loaded. No redundant or extra information, every sentence adds value.

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

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

Given no output schema and moderate complexity, the description lacks details on the output format (list vs diff). It mentions 'shows concepts' but not how they are presented. Siblings imply more context might be needed, but description is adequate for basic use.

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% for the single parameter 'since', which has a clear description in the schema. The tool description does not add extra meaning beyond what the schema provides, so baseline 3 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 clearly states the tool compares domain ontology between two git revisions, showing added, removed, or changed concepts. This is a specific verb and resource, and distinguishes from sibling tools like list_concepts or concept_map.

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 it is useful for understanding vocabulary evolution and PR review, providing clear usage context. It does not mention when not to use or alternative tools, but the context is strong enough for a 4.

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?

While no annotations are provided, the description discloses that the tool returns multiple types of information in one call and gives a detailed example of query expansion. It does not explicitly state read-only or side-effect-free, but the name and context imply a query operation. Lacks some nuance like whether results are cached or ordered, but sufficient for most use cases.

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 sentences plus a usage tip, all front-loaded with the core purpose. No filler, 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?

Given the tool has 5 optional parameters and no output schema, the description covers the return types (variants, related concepts, etc.) reasonably well. It differentiates from grep but not from sibling tools like concept_map or locate_concept, which may overlap. Still, it's sufficiently complete for a query 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 100%, so the schema already documents all parameters. The description adds no additional parameter-level meaning beyond the schema, e.g., no format constraints or examples. Baseline 3 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 clearly states the tool does a 'semantic concept lookup' returning variants, related concepts, naming conventions, function signatures, and file locations. It distinguishes from grep with a concrete example (querying 'transform' finds 'trf', etc.), making the purpose specific and actionable.

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 when to use: 'when asked what is X, what does X mean, or where is X used'. Also contrasts with grep as an alternative, providing clear usage context without needing negative examples.

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?

Describes that it uses project conventions and suggests names fitting existing style. No annotations provided, so description carries full burden; it adequately conveys the tool's behavior without contradictions, but could mention that it does not modify anything.

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 succinct sentences that are front-loaded with the core purpose, 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?

For a single-parameter tool with no output schema, the description is mostly complete. It could clarify the return format (e.g., list of suggested names), but the essential purpose and usage are clear.

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% with a description for the 'description' parameter. The tool's description adds an example ('count of features'), enhancing understanding beyond the schema alone.

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

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

Clearly states it generates identifier names from natural language using project conventions, with specific examples of patterns. Distinguishes from siblings (e.g., check_naming) by focusing on generation rather than validation.

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 specifies 'Use when naming new functions, variables, or parameters.' Provides clear context for when to use, though does not mention 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?

With no annotations provided, the description provides substantial behavioral detail: it returns an ordered call chain with file locations and producer/consumer roles, and includes bridge functions on the path. It does not mention side effects or safety, but the read-only nature is implied. The description goes a long way in disclosing behavior beyond the basic purpose.

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 only three sentences, each serving a clear purpose: first sentence states the main purpose and what it shows, second describes the return value, third provides example queries. No wasted words, front-loaded with the core 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 tool has no output schema, the description adequately explains the return value (ordered call chain with locations and roles). It covers the key inputs (concept, depth) and what they affect. The description is complete enough for an agent to understand what the tool does and what it returns, even in the context of 18 sibling 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?

The input schema has 100% description coverage; the schema itself describes 'concept' as 'The concept to trace (e.g. "transform")' and 'max_depth' as 'Maximum call chain depth (default: 5)'. The description does not add significant meaning beyond what the schema provides, only mentioning 'maximum call chain depth' implicitly. Thus, it meets the baseline but does not exceed it.

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

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

The description clearly states the tool's purpose: to trace how a domain concept flows through code via function call chains. It specifies what it shows (producers, consumers, call paths, file locations, roles) and uses specific verb phrases like 'trace', 'shows', 'returns'. The name 'trace_concept' is accurately described, distinguishing it from siblings like 'trace_type' or 'type_flows'.

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: when asked about concept propagation, 'what calls what for X', or 'trace X through the code'. It implies exclusion of other sibling tools (e.g., trace_type for types) but does not explicitly mention when not to use it. Overall, clear context is provided.

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 burden. It discloses the tool outputs edges and functions passing/receiving the type, but lacks details on potential constraints (e.g., only call edges) or side effects. Adequate but not rich.

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: two sentences that front-load the purpose and immediately provide usage examples. No wasted words; every sentence 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 simple tool with one parameter and no output schema, the description is complete. It explains what the tool does, how to use it with examples, and the kind of output (edges, functions). No gaps for this complexity level.

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% for the single parameter. The description adds context by explaining how the type_name parameter is used to find edges, going beyond the schema's description. The baseline is 3 but the additional explanation justifies a 4.

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 finds all data-flow edges involving a specific type and shows which functions pass/receive it. It provides concrete example queries ('where does Tensor flow') that distinguish it from sibling tools like trace_concept.

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 scenarios with example queries, telling the agent when to use this tool. However, it does not mention when not to use it or provide alternatives, missing some guidance for exclusion.

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 three types of data: edges, dominant types, and counts. This gives insight into the tool's behavior without stating side effects, but is sufficient for a read-only analysis 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?

Three sentences, each adding distinct information. Front-loaded with the main action. No redundancy or waste.

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 description must explain return values. It covers edges, dominant types, and counts, but lacks detail on format or structure. Acceptable for a zero-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?

Input schema has zero parameters, so description cannot add param info. Baseline 4 applies. The description adds value by explaining output, which is relevant when no params are expected.

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 specifies a clear verb ('trace') and resource ('types flowing through codebase along call edges'). It distinguishes from siblings like 'trace_type' by focusing on global dominance analysis rather than tracing a single type's path.

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 (e.g., trace_type for specific type tracing). The description only states what it does, 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?

No annotations are provided, so the description carries the full burden. It discloses that the tool returns an overall score plus top inconsistencies and uncovered identifiers. It does not mention side effects (likely none). Could benefit from stating that it is a read-only operation.

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

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

Three sentences, each adding value: purpose, usage guidance, and output description. No redundant or extraneous information.

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 output schema, the description clearly explains the return value (overall score plus top inconsistencies and uncovered identifiers). This is sufficient for an agent to understand the tool's output.

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

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

The input schema has no parameters, so schema description coverage is effectively 100%. The description adds value by explaining the metrics returned, which compensates for the lack of parameter documentation.

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 measures vocabulary health with three specific metrics (convention coverage, consistency ratio, cluster cohesion). It uses a specific verb+resource and distinguishes from sibling tools like check_naming and suggest_name.

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 usage context: 'Use when asked about code quality, naming consistency, or vocabulary health.' No exclusions or alternatives are mentioned, but given the tool's specificity, it is sufficient.

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