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

No annotations are provided, so the description must disclose all behavioral traits. It only states it adds an alibi and lists status options, but does not mention consequences like overwriting existing alibis, validation rules, 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?

The description is two sentences, with the main action in the first sentence and clarifying detail in the second. 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 simple creation tool without output schema or annotations, the description covers purpose and status but lacks information on return values or post-conditions, making it moderately 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?

The description adds value by explaining the status enum values and indicating the default. However, with 50% schema coverage, the description does not fully compensate for the lack of detail on other parameters like start and end formats.

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 'Add an alibi to a specific person' with verb and resource, and specifies the status enum, distinguishing it from siblings like add_person or add_record.

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 the default status but no explicit guidance on when to use this tool versus alternatives or prerequisites. The purpose is clear, but usage context is implied rather than stated.

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

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

With no annotations, the description must disclose behavior. It only says 'adds a relationship' but does not mention side effects (e.g., creates records), error conditions, authorization, or idempotency. This is minimal disclosure for a mutation 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?

Two short, clear sentences with no extraneous information. The description is appropriately sized and front-loaded with the core 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?

Given the domain (cases, persons), the description lacks context about the caseId parameter and how edges relate to existing data. No output schema, so the agent doesn't know what to expect. The description is insufficient for a complete understanding of the tool's function.

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 'from' and 'to' parameters as local IDs and gives label examples, adding value beyond the schema. However, it fails to explain the 'caseId' parameter, which is crucial for the context. Schema coverage is 0%, so the description partially compensates but remains incomplete.

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

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

The description clearly states the verb 'adds' and the resource 'relationship between two people', distinguishing this from other tools like add_person or add_alibi. However, it does not explicitly differentiate from siblings or provide scope. It is specific enough for basic understanding.

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, nor any prerequisites or constraints. The description only provides label examples but omits context like required existing persons or case setup. The agent lacks direction for appropriate invocation.

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

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

No annotations provided, so description must disclose behavioral traits. It mentions returning a local id but does not describe side effects, permissions, or constraints like duplicate name handling.

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, front-loading the purpose and providing a clear example. 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 11 parameters and no output schema, the description is too brief. It lacks prerequisites, error conditions, and return format beyond 'local id'. Incomplete for a creation 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 low (36%), but the description only elaborates on the 'roles' parameter with examples. Other parameters (note, notables, x, y) have schema descriptions, but the description adds no extra 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 it adds a person to a case and provides example roles. It distinguishes from siblings like add_alibi by specifying the resource type.

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

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

No explicit guidance on when to use this tool versus alternatives like add_alibi or add_edge. The description only states the function without context.

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 mentions the action ('add') implying mutation, but does not disclose side effects, permissions required, idempotency, or error behavior. The only behavioral detail is that time can be omitted.

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

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

The description is concise: one sentence stating the purpose followed by a clarifying note on the time parameter. It is front-loaded with the core action. 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 output schema, no annotations, and three parameters, the description is insufficient. It omits return behavior, data constraints for content, and the overall scope of 'record'. An agent would lack enough context to use this tool effectively.

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

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

Schema coverage is 0%, so the description must compensate. It explains the time parameter (format and optionality), but says nothing about caseId (required it is) or content (required, minLength). The description adds value for time only, leaving two parameters unaddressed.

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 adds a case record. It uses a specific verb and resource ('add record'), but does not differentiate from sibling tools like add_alibi or add_person, which are more specific record types. The clarity is good but could be more distinguishing.

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

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

The description provides a guideline for the time parameter format ('datetime-local string'), but lacks any guidance on when to use this tool versus alternatives (e.g., add_alibi for alibis). No context on prerequisites or typical use cases is given.

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

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

Discloses basic behavior: creates a case and returns UUID. No annotations provided, so no contradiction. Lacks detail on side effects, idempotency, or authorization.

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, front-loaded with action, 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 6 parameters, no output schema, and full schema descriptions, the description is fairly complete. Could mention duplicate name handling or error behavior.

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%, baseline 3. Description adds meaning by specifying return value and reinforcing optionality of non-name fields.

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 'Creates a new case' with required vs optional fields and return value. Distinguishes from sibling tools like update_case_info and list_cases.

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?

Implied usage: use when creating a new case. No explicit guidance on when not to use or alternatives; e.g., for updates use update_case_info.

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 effectively discloses that deletion is permanent and cascades to child data (people, alibis, records). This covers the key behavioral traits for a delete 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?

Two sentences, no superfluous words. The main action is front-loaded, and the critical behavioral warning is provided succinctly.

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

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

Given the simple nature of the tool (single param, no output schema), the description covers the essential behavioral aspects. It does not address error handling or how to retrieve the ID, but these are not necessary for basic 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?

The input schema has 0% description coverage, and the tool description does not explain the 'id' parameter. Although the parameter's purpose is inferable from context, the description fails to add any explicit meaning 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's action (permanently delete a case) and the resource (case). It distinguishes from siblings as there are no other delete tools among the listed siblings.

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 warns about irreversibility and cascading deletion, guiding the agent to use it only when certain. No explicit 'when not to use' is given, but the context makes it clear this is the dedicated delete tool.

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 adds behavioral context about the result containing a url link, but does not explicitly state that the tool is read-only or disclose any authorization requirements or 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?

The description is two sentences with no extraneous words. The first sentence states the main functionality, and the second adds a useful detail about the URL. Information 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 the complexity of returning full case detail and the absence of an output schema, the description adequately lists the components (overview, persons, etc.) and mentions the URL. It does not describe output structure, but the listed components provide sufficient context.

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 one parameter (id) described as '사건의 UUID'. The description repeats that the tool returns case content but adds no additional semantics about the parameter, such as format or constraints, staying at the baseline for high 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?

The description uses a specific verb '반환합니다' (returns) and identifies the resource as '사건 한 건의 전체 내용' (entire content of one case), listing specific components. This clearly distinguishes it from sibling tools like list_cases (which lists cases) and update_case_info (which updates).

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 no guidance on when to use this tool versus alternatives. It does not specify that this is for retrieving full detail vs. summary, nor does it mention alternatives like list_cases for overviews.

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, but the description discloses that it returns metadata only (not full details) and includes a url for direct access. Since it's a read operation, it appropriately avoids side-effect claims. However, it does not mention authentication or rate limits.

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

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

The description is a single sentence that is front-loaded and concise. Every part is meaningful: it states the action, the scope, the content, and an instruction to expose the url.

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 and no output schema, the description is complete. It specifies the scope ('current user'), the return type (metadata only), the fields, and an actionable instruction for the agent (expose url).

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?

There are no parameters, and schema coverage is 100%. The description adds value by detailing the output structure (id, name, occurrence, location, summary, counts, url) beyond what an empty schema 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 it returns the current user's case list (metadata only) and enumerates the fields (id, name, occurrence, location, summary, counts, url). It distinguishes from siblings like get_case_detail by specifying 'metadata only'.

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 specifies it's for listing cases and provides context about the output. It does not explicitly state when not to use it or name alternatives, but from sibling tool names (create_case, delete_case, get_case_detail), the usage 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?

The description explicitly states that only passed fields are changed (partial update), which is valuable behavioral information. However, with no annotations and no output schema, it omits details on idempotency, authorization needs, return format, and error conditions.

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

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

The description is a single sentence, which is concise but arguably too terse. It communicates the core behavior without superfluous content, but could benefit from additional context without becoming verbose.

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

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

Given the tool has 7 parameters, no output schema, and no annotations, the description fails to provide adequate context. The agent does not know what the tool returns, how to format dates, or what 'occurrenceError' represents. This is insufficient for reliable invocation.

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

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

Schema coverage is 0%, so the description must compensate. It adds the concept of partial updates but does not describe any individual parameter (e.g., what 'occurrence' or 'occurrenceError' mean). This minimally helps the agent understand the update mechanism but leaves parameter semantics largely unaddressed.

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 modifies fields of the case summary and specifies partial update behavior. The verb 'modify' and resource 'case info' are distinct from sibling tools like create_case or delete_case. However, it does not enumerate which fields belong to the 'overview', leaving some ambiguity.

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

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

No guidance is provided on when to use this tool versus alternatives (e.g., add_record, create_case). The description does not specify prerequisites or situations where this tool is inappropriate.

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