wwise-mcp

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

With no annotations, the description bears the full burden. It mentions the two-step 'plan/apply' approach and that it is undoable, providing some insight into behavior. However, it does not disclose side effects, permissions, or the scope of the operation beyond what is implied.

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, using two sentences to convey purpose and a key behavioral detail. Every word contributes value 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?

Despite conciseness, the description lacks explanation for the required 'mode' parameter and other key inputs. Without output schema or annotations, an agent cannot fully understand how to invoke the tool correctly. The two-step process is mentioned but not detailed, leaving the agent guessing about the workflow.

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 that 'reference' should be 'Attenuation' or 'Conversion', adding value beyond the schema which has no descriptions. However, the other four parameters (mode, object_ids, shareset, token) are not explained, leaving significant gaps given 0% schema 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 clearly states the action ('batch-assign'), the resource ('Attenuation or Conversion ShareSet'), and the target ('objects'). It distinguishes the tool from siblings like wwise_set_properties or wwise_soundbank_assign by specifying the type of shareset and the batch nature.

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 hints at a two-step plan/apply workflow but does not explicitly state when to use this tool versus alternatives like wwise_set_properties. No guidance on prerequisites or exclusion criteria.

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 the tool is read-only and discloses a limitation (WAAPI does not expose sample rate/channels). This adds behavioral context beyond the tool name. However, it does not mention any other side effects or permissions required.

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

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

The description is three concise sentences. The first sentence states the main action, the second clarifies read-only nature, and the third adds a limitation. No unnecessary words; every sentence provides 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 zero parameters and no output schema, the description covers the main checks and read-only nature. However, it does not describe the output format (e.g., list of flagged sources or summary), leaving some ambiguity about what the tool returns.

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, so baseline is 4. The description does not need to add parameter details since there are none. It effectively explains what the tool operates on without requiring parameters.

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 audio sources and flags two specific conditions: sources without original WAV path and original files used by multiple sources. The verb 'Audit' and resource 'audio sources' are specific, and the tool is distinct from siblings like wwise_audit or wwise_compat_check.

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. It implies usage for file integrity checks, but does not specify when not to use it or provide comparisons to other audit-related siblings. The note about WAAPI limitations is helpful context but not a usage guideline.

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 effectively discloses read-only nature, default checks, and that the findings list is capped (matching the 'max_findings' parameter). Behavior is well explained.

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 states purpose and read-only nature, second lists checks and output. Efficient and 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 2 parameters, no output schema, and no annotations, the description is complete enough for an audit tool. Could optionally mention that results are returned immediately (not real-time).

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%, but description fully explains the 'checks' parameter (list of specific check names, default all) and 'max_findings' parameter (cap on findings). Adds semantic 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?

Clearly states it is a 'Read-only project health audit', lists specific checks, and describes output format (counts + findings list). This distinguishes it from siblings like 'wwise_fix_all' (fixes) and 'wwise_inspect' (inspects).

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 for project health auditing, but no explicit guidance on when to use this tool versus others (e.g., wwise_status, wwise_compat_check). No prerequisites or conditions mentioned.

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 declares the tool as 'Read-only', which is a key behavioral trait. In the absence of annotations, this disclosure is valuable and sufficient for a simple tool with no side effects. However, no further details on output format or performance implications are provided.

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, efficient sentence with no wasted words. It conveys the essential information in a clear and front-loaded manner.

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 parameterless, read-only tool without an output schema, the description is adequately complete. It states what the tool counts and that it is read-only. Minor improvement could include mentioning the output is a count per bus, but it is not necessary given the 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?

Since there are zero parameters and schema description coverage is 100%, the description does not need to add parameter semantics. The description adds context by explaining the purpose, which is beneficial beyond the empty 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 a specific action ('Count') and resource ('objects routing to each Output Bus'), with a clear purpose ('mix-routing overview'). It effectively distinguishes this tool from siblings like wwise_audit or wwise_query by specifying a focused, numeric output.

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

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

The description implies usage for obtaining a bus routing count but does not explicitly state when to use this tool over alternatives or provide exclusions. No guidance on prerequisites or when not 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?

Describes the tool's intended output but does not explicitly state that it is non-destructive or detail any side effects, which would be more transparent given no annotations are present.

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-load the core purpose and usage advice, with 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?

Adequately covers the tool's main function and usage context, though it could clarify prerequisites like needing a connection to Wwise running.

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 exist, and schema coverage is 100%, so baseline score applies; no additional parameter semantics needed.

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

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

The description clearly states the tool reports the connected Wwise version and expected tool compatibility, which distinguishes it from sibling tools that perform specific actions like assigning or checking files.

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

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

Explicitly advises to run this tool first on an untested Wwise version for self-diagnosis, providing clear context on when to use it, though it doesn't name alternatives.

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

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

No annotations are provided, so the description carries the full burden. It discloses the two-step behavior, token flow, and undoability. Missing details on authorization or limits, but adequately describes the core behavioral traits.

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

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

Two concise sentences: first states the main operation, second details the two-step mode. No redundant information, front-loaded key 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 5 parameters, no output schema, and a complex two-step process, the description covers the essential workflow and undo feature. Minor gaps exist (e.g., token validity, scope of undo), but overall it is 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?

With 0% schema description coverage, the description partially compensates by explaining mode and token semantics, but does not elaborate on object_ids, container_name, or container_type beyond mentioning the default.

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 specific verbs ('Wrap', 'previews', 'creates+moves') and clearly identifies the resource ('objects into a new container'). It distinguishes from sibling tools like wwise_move and wwise_create_events by describing a unique two-step container creation process.

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 explains the two-step mode ('plan' preview and returns token, 'apply' creates/moves) and notes undoability. However, it does not provide when-not-to-use guidance or compare with alternatives.

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

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

Without annotations, the description compensates by detailing the two-step safety, idempotency, undoability, and default handling. It could elaborate on the preview output but still provides substantial behavioral context.

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 efficiently cover the core action, safety workflow, defaults, and edge cases without redundancy. Front-loaded with the main 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?

The description covers the tool's purpose, modes, default behavior, and scope of operation. Given no output schema, it could specify what the plan mode preview returns, but still provides a solid understanding 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?

With 0% schema coverage, the description adds essential meaning to all parameters: explains mode values, token role, prefix default, and object_ids omission. The token's origin from plan mode is implied but not explicit.

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 creates Play events for Sounds that lack one, specifying the naming pattern and default prefix. It distinguishes the tool's unique safety workflow among 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?

It explains the two-step plan/apply modes and when each is used, and mentions behavior when object_ids is omitted. However, it does not explicitly exclude alternatives or state when not to use.

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?

Without annotations, the description carries full burden. It discloses that the tool returns markdown and optionally writes to a file, but omits details like overwrite behavior, project state requirements, or side effects. The behavioral disclosure is minimal but not misleading.

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

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

The description is two concise sentences. The first sentence immediately states the tool's purpose, and the second covers the return value and optional file write. No extraneous information, making it easy to scan.

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

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

For a simple export tool with one optional parameter and no output schema, the description covers the key aspects: what it generates, return type, and optional side effect. It could mention the target project or format limitations, but overall is adequate.

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 coverage is 0%, so the description must explain parameters. It successfully adds meaning for the single parameter `output_path` by clarifying it is an optional file write path. This compensates for the schema's lack of 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 generates a Markdown audio-design doc with specific components (project summary, event list, Mermaid bus hierarchy). This is a specific verb-resource pairing that distinguishes it from sibling tools like wwise_audio_file_check or wwise_audit.

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

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

The description implies usage when a project documentation export is needed, but lacks explicit when-to-use or when-not-to-use guidance. It does not mention alternatives or prerequisites, leaving the agent to infer the context from the tool name and description alone.

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 fully discloses behavior: it renames whitespace names, adds events to default_bank, sets default_bus, and only reports issues needing human intervention. The dry_run parameter behavior is explained. Lacks details on potential side effects like overwriting.

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 effectively convey the tool's purpose, behavior, and workflow. No superfluous words, 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 output schema and 4 parameters, the description covers main behavior and workflow. It could mention that fixes are project-wide, but overall sufficient for an agent to use correctly.

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

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

Despite 0% schema coverage, the description explains dry_run, default_bank, and default_bus. However, the 'fixes' parameter is not mentioned, leaving its purpose unclear. The description adds value for three of four parameters.

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 and auto-fixes specific issues (whitespace names, events not in SoundBank, sounds with no Output Bus). It distinguishes from sibling tools like wwise_audit and wwise_rename by combining audit with automatic fixes.

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 clear workflow: run dry_run=True first to preview, then dry_run=False to apply. It implies usage vs. alternatives (e.g., wwise_audit for auditing only) but does not explicitly state when not to use this 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 must carry the burden. It discloses that the tool returns all property/reference values, parent, children, and action targets for Events. However, it does not explicitly state that it is read-only, nor does it mention any side effects, auth needs, 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?

Two sentences: first states the purpose and what it returns, second details the parameter format. No wasted words, 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 one required parameter, no output schema, and no annotations, the description covers the purpose, return content, and parameter format. It could mention the output structure (e.g., JSON format), but it is largely complete for a simple 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?

The schema has 0% description coverage for the 'object' parameter, but the description compensates by specifying acceptable formats (GUID, path, or name), adding meaning beyond the schema's bare type definition.

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 performs a deep dive on one object, listing all property/reference values, parent, children, and for Events, action targets. This specific verb and resource distinguishes it from siblings like wwise_query or wwise_set_properties.

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

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

The description explains acceptable formats for the 'object' parameter (GUID, path, name), but does not specify when to use this tool versus alternatives like wwise_query. Usage context is implied but explicit exclusions are missing.

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 full burden. It discloses idempotency (objects already there are skipped) and undoability, which are key behavioral traits. It also mentions the two-step plan/apply nature, adding transparency beyond the basic 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 unnecessary words. The most critical information is front-loaded: action and target specification. 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 the two-step workflow and four parameters, the description covers idempotency, undoability, and parent types. But it lacks explanation of the plan/apply process (e.g., what plan returns) and return values, leaving the agent with incomplete context 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 coverage is 0% (no descriptions on parameters). The description adds meaning for 'parent' (accepts GUID, path, or name) and hints that 'mode' relates to plan/apply. However, it does not explain 'object_ids' or 'token', leaving gaps.

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 reparents objects and specifies the target parent can be given as GUID, path, or name. This distinct action differentiates it from sibling tools like wwise_create_container or wwise_rename.

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 mentions a 'Two-step plan/apply' workflow, implying a sequence of calls, and notes idempotency and undoability. However, it does not explicitly state when to use this tool versus alternatives or provide exclusion criteria.

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 states the tool is read-only, which is critical for behavioral understanding. However, it omits details like scope (all objects in project?), whether it modifies anything, or limits on findings. The transparency is 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 extremely concise: one sentence plus 'Read-only.' It front-loads the core action and avoids unnecessary words. Every token 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 3 parameters, no output schema, and no annotations, the description is incomplete. It does not explain types or max_findings, nor does it describe the output format. The agent lacks sufficient context to confidently invoke the tool without guessing.

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

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

Schema description coverage is 0%, so the description must compensate. It explains pattern as a regex for optional checking, but types and max_findings are not mentioned. The agent cannot infer the meaning or constraints of these parameters from the description 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?

The description clearly identifies the tool as flagging objects with naming-convention issues (whitespace, non-ASCII) and optionally checking against a regex pattern. 'Read-only' clarifies the operation type. This distinct purpose separates it from sibling tools like wwise_audio_file_check or wwise_audit.

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 sibling tools. It does not specify prerequisites, typical scenarios, or exclusions such as 'use wwise_audit for broader checks.' The agent must infer usage from the name alone.

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 responsibility for behavioral disclosure. It explains the one-shot nature, that each step is undoable, and stage activation logic. It lacks details on auth or rate limits, but covers the core workflow well.

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 waste. The first sentence defines the tool's purpose and chain; the second provides critical usage guidance. Well-structured and 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 7 parameters, no output schema, and no annotations, the description provides sufficient context for invocation (chain, dry-run, stage activation). Missing is the return value or success/failure indication, but the description is otherwise complete 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 description coverage is 0%, so the description must compensate. It links parameters (conversion, container_name, output_bus, soundbank) to the pipeline stages and explains the dry_run flag and event_prefix. The object_ids parameter is not explicitly explained, but 'make these sounds playable in-game' provides context.

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 is a one-shot pipeline to make sounds playable in-game, detailing the chain (conversion, container, events, bus, SoundBank). It distinguishes itself from sibling tools like wwise_create_container or wwise_soundbank_assign, which handle individual steps.

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 recommends running with dry_run=True first, then dry_run=False to execute, and clarifies that only stages with provided arguments run. It does not explicitly list alternatives, but the sibling tools are more granular, implying this is the high-level orchestration.

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 conveys read-only behavior and capping of results, but lacks details on authentication, rate limits, or what happens on empty results.

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 with no wasted words. It includes an example and key constraint (capped results).

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 with zero description coverage, the description is insufficient. It lacks return format, parameter details, and behavioral nuances, making it incomplete 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 0%. The description provides an example for 'waql' but does not explain 'fields' or 'max_results' parameters. 'max_results' is weakly implied by 'results are capped', but 'fields' is entirely unexplained.

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 'Run a read-only WAQL query against the open Wwise project' with an example query. This distinguishes it from sibling tools that perform other actions like creating, moving, or generating soundbanks.

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 is a read-only query and mentions results are capped, giving some usage context. However, it does not explicitly state when not to use it or compare to alternatives like wwise_inspect.

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 the two-step workflow, default transform, and important behaviors like 'verified by read-back' and 'undoable'. It does not cover all aspects (e.g., scope of objects), but covers core behavioral traits.

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

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

Two sentences, front-loaded with purpose. Every word adds value. No fluff or repetition. Exemplary conciseness.

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

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

Given 4 params, no output schema, no annotations, the description is incomplete. Missing explanation of 'types' parameter and the scope of objects affected. While it covers key aspects, these omissions reduce completeness.

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

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

Schema coverage is 0%, so description must compensate. It explains mode, transform (with default), and token. However, the 'types' parameter is not mentioned, leaving a gap. Partial but not complete 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 ('Batch-rename') and resource ('objects'), explains the transform method with a default example, and clearly distinguishes this tool from siblings (no other rename tool). It's comprehensive and unambiguous.

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 details the two-step process (plan then apply) and explains when each mode is used. It does not mention when not to use the tool or alternatives, but the guidance within the tool 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?

With no annotations, the description fully bears the burden of behavioral disclosure. It clearly states that plan mode performs no writes and returns a ChangeSet+token, while apply mode executes changes. This transparently communicates the safety behavior.

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-loaded with purpose, and wastes no 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?

The description explains the two-step process but does not specify what the apply mode returns or potential error states. Given no output schema, this information would enhance completeness.

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

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

Schema description coverage is 0%, so the description must compensate. It adds meaning for 'mode' (plan/apply) and 'token' (returned from plan), but for 'object_ids', 'property', and 'value' it only implies their purpose via the first sentence. Minimal added value beyond parameter names.

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 'Batch-set' and resource 'property on objects', and introduces a two-step safety mechanism that distinguishes it from sibling tools. The purpose is 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?

The description provides explicit usage guidance: use mode='plan' for previewing changes and mode='apply' with the returned token to execute. This forms a clear workflow, though it does not compare to alternatives or specify when not 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?

With no annotations, the description carries full burden. It discloses the two-step process, idempotency, undoability, and token usage. It does not cover error cases or side effects, but adds meaningful behavioral context beyond just naming.

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, front-loaded with the primary action and workflow. Every sentence adds value with no redundancy.

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

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

Given the complexity (two-step process, 4 params, no output schema, no annotations), the description explains the workflow but lacks parameter details and return value expectations. It is adequate but incomplete.

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

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

Schema description coverage is 0%, so the description should explain parameters. It hints at 'mode' and 'token' but does not define 'soundbank' or 'object_ids' formats or values. Critical semantic details are missing.

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: adding objects to a SoundBank's inclusion list by bank name or id. It specifies the two-step process, making it distinct from sibling tools like wwise_soundbank_generate which focuses on generation.

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 clear context on the two-step mode workflow and mentions idempotency and undoability. However, it does not explicitly guide when to use this tool over alternatives, such as when not to use it or prerequisites.

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

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

With no annotations, the description carries the burden. It clarifies it's an action that writes output and returns a log summary, but lacks details on overwriting, permissions, 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?

Two sentences, no extra verbiage. Key information is front-loaded: action, default behavior, and distinction from project data.

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 optional parameter and no output schema, the description covers the core functionality and return value. Could mention prerequisites like an open project, but not critical.

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?

Description adds meaning for the 'soundbanks' parameter: omitting generates all. Schema coverage is 0%, so description compensates partially, but doesn't explain array item semantics (bank names?).

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 the action 'Generate SoundBanks to disk' and distinguishes from siblings by noting it writes output, not project data. The default behavior (all banks if omitted) is explicit.

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?

Implies when to use (generate banks to disk) and when not (not for modifying project data). However, no explicit alternatives or exclusions are 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?

No annotations are provided, so the description must convey behavior. It clearly states it checks connection and reports the project, which is accurate and non-destructive. However, it could mention that it has 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?

A single sentence that is concise and front-loaded, containing no unnecessary words or repetition. Every part of the description 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?

For a parameterless tool with no output schema, the description provides adequate context on what the tool does. It could optionally mention the output format, but this is not required for completeness.

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

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

There are no parameters, so the schema coverage is 100% trivially. The description adds meaning by explaining the tool's purpose beyond the empty schema, earning the baseline 4 for zero parameters.

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 the connection to Wwise and reports the open project, which is a specific verb+resource that distinguishes it from other Wwise tools like wwise_assign_shareset or wwise_audit.

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

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

The description implies the tool should be used to verify connectivity and project status, but it does not explicitly state when to use it versus alternatives, nor does it provide exclusions or prerequisites.

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

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

No annotations are provided, so the description must carry the full burden. It discloses the scanning behavior (PostEvent string literals under unity_path), the comparison against Wwise events, and the two types of reports generated. The limitation about enum IDs is also noted.

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 long, each sentence adds essential information with no redundancy. It is front-loaded with the purpose and efficiently covers scope, method, and limitations.

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

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

Given the tool's complexity (scanning, diffing, reporting) and no output schema, the description adequately explains what the tool produces: two types of reports. It does not detail the output format, but the core behavioral output is 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 0%, so the description needs to compensate. It implicitly describes 'unity_path' as the directory to scan, but does not explain 'max_findings' at all. This partial coverage gives some value beyond the schema but is 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 tool cross-checks Unity C# event usage against Wwise events, using specific verbs like 'Cross-check' and 'Scans'. It distinguishes itself from sibling tools by focusing on the code-Wwise discrepancy check.

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

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

The description explains when to use the tool (to find discrepancies) and includes a key limitation: 'String-literal calls only; enum IDs not detected.' This helps an agent decide whether the tool is applicable, but it does not explicitly state when not to use or mention alternatives.

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