sonicaura-mcp

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

With no annotations, the description carries full behavioral burden but discloses nothing: not whether processing is destructive to the source, whether it consumes credits (a sibling get_my_credits implies metered operations), how long it takes, or whether it is async (siblings check_task_status suggest long-running tasks).

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 words are not concise but under-specified; there is no front-loaded statement of action, inputs, or effect. Nothing is wasted because nothing is said, which is a failure of content rather than verbosity.

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 4-parameter processing tool with no annotations, no output schema, and zero schema coverage, the description provides none of the missing context. An agent would have to guess at input format, side effects, and return behavior before invoking it.

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% across all four parameters, and the description compensates for none of it. The opaque required `kwargs` string, the `source_key` identifier, the `preset` default of studio_room, and the `format` default of mp3 are all left unexplained in both places.

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?

"AI Sound Reverb" restates the tool name (apply_reverb) rather than describing the action, its input, or its output. It is at least suggestive that audio reverb processing occurs, but it offers no verb-and-resource description and no differentiation from siblings like denoise_audio or split_4stems.

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?

There is no guidance on when to use this tool, when not to, or which sibling alternatives exist. An agent cannot infer from three words whether reverb should be applied before or instead of denoise_audio or the stem-splitting tools.

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

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

No annotations are provided, so the description carries the full behavioral burden. It implies a read-only probe but says nothing about auth requirements, rate limits, or what an 'available' vs 'unavailable' result looks like. For a zero-annotation tool with no output schema, this is a real gap.

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?

One short sentence, front-loaded with the verb and resource, and every word earns its place. No filler or restatement of the title.

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 trivial zero-parameter status probe the description covers the essentials. Since there is no output schema, it would be marginally stronger if it hinted at the return shape (boolean vs status payload), but the gap is minor for a tool this simple.

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

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

The tool takes zero parameters, which is the baseline-4 case. Nothing about arguments needs explaining and the description does not waste words on them.

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?

States a specific verb (Check) plus resource (SonicAura audio service) and the dimension being checked (availability). It is implicitly distinguishable from siblings like check_separation_status and check_task_status via the word 'service', but it never explicitly contrasts them, so it stops short of a 5.

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 when-to-use guidance, no prerequisites, and no mention of alternatives or follow-up tools. The agent can only infer that this is a pre-flight health check from the name; nothing in the description says when to call it instead of, say, check_task_status.

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 and mostly doesn't: read-only-ness is only implied by "check," and there is no mention of polling cadence, what statuses are returned, whether results disappear after completion, or what happens with an invalid or expired task_id. The one useful disclosure is that the response auto-includes detected tracks, MIDI, and chords.

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 sentences, front-loaded with the action and followed by the one operational hint. Nothing is padded, though the brevity comes at the cost of the missing details noted above.

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?

There is no output schema and no annotations, so the description should explain return shape and status semantics; it only gestures at the contents (tracks, MIDI, chords). For an async status-polling tool with an undocumented kwargs parameter, this leaves an agent without enough to call it confidently.

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% for two required parameters, so the description must compensate and doesn't. task_id gets only "just pass task_id" with no format or origin, and the required "kwargs" string parameter is not mentioned at all, leaving an agent guessing what to supply.

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?

States a specific verb and resource ("Check the status of a task") and adds scope by naming what the result covers: generated tracks, MIDI, and chords. It is clear enough to act on, but "task" is never tied to the audio-generation jobs implied by the sibling list, so an agent must infer the domain.

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?

"Just pass task_id" hints at polling an async job but gives no explicit when-to-use guidance, no prerequisite (that a job must have been submitted first), and no terminal-state behavior. It also fails to distinguish itself from the sibling check_service_status, which is the most likely source of confusion.

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 behavioral burden. It implies an audio transformation but says nothing about async execution, required audio upload/source key, credits, output handling, or whether the operation creates a new file.

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 very short and front-loaded, with no verbose filler. However, its brevity is partly under-specification rather than optimal conciseness for a four-parameter tool.

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

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

Given no annotations, no output schema, 0% schema description coverage, and four parameters including required source_key and kwargs, the definition is not complete enough. It lacks essential context about input format, async behavior, and return values.

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%, yet the description explains only the mode parameter values. It does not clarify source_key, kwargs, or format, leaving three of four parameters undocumented in both schema and 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 a specific verb and resource: denoising audio, with a music/speech mode distinction. It does not explicitly differentiate itself from sibling audio tools, but the purpose is still clear.

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 only says mode='music' or 'speech', which is parameter value guidance rather than when-to-use guidance. It does not explain when to choose denoise_audio over siblings such as extract_vocals or split_4stems, nor does it state prerequisites 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 behavioral burden, and it discloses nothing: not whether the operation writes to disk or returns data, what authentication or credits it consumes, whether it is idempotent, or what errors are possible. 'Export' implies a mutation/side effect but this is never clarified.

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?

Extremely short, but here brevity reflects under-specification rather than efficiency. There is only a four-word fragment with no structure to speak of.

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

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

For a tool with three required parameters, no annotations, and no output schema, the description supplies essentially nothing about inputs, behavior, or results. It is wholly inadequate for correct 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?

Three required parameters (source_key, instrument, kwargs) with 0% schema description coverage and no explanation in the description. The opaque 'kwargs' string parameter is particularly undocumented, leaving the caller unable to construct a valid call.

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 'AI MIDI Export' essentially restates the tool name export_midi and adds only the vague qualifier 'AI'. It does not specify what is being exported from, what format or content the MIDI contains, or how it differs from siblings like extract_chords or extract_single_instrument.

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 when-to-use guidance, no prerequisites, and no mention of any alternative tool. An agent has no basis for choosing this over the other twelve 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?

No annotations are provided, so the description carries the full burden and delivers nothing: no indication of whether this is synchronous or async (siblings like check_task_status suggest task polling is common in this family), whether credits are consumed, expected audio formats or duration limits, or failure 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?

It is short, but the brevity is under-specification rather than concision: a three-word fragment that front-loads nothing actionable. No sentence here earns its place because no sentence conveys operational 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?

With two required parameters, 0% schema coverage, no annotations, and no output schema, the description must explain inputs, async behavior, and results — it explains none of them. Nothing an agent needs to invoke this tool correctly is present.

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% and the description adds no parameter meaning at all. The required 'kwargs' parameter is an opaque string with no documented format and 'source_key' is unexplained, so an agent cannot construct a valid call from either source.

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?

"AI Chord Recognition" names a capability but only restates the tool name (extract_chords) without adding a verb of action on inputs. It does not say what it operates on (an uploaded audio file referenced by source_key) or what it returns, so an agent cannot distinguish it from sibling extractors beyond guessing from the noun 'chords'.

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?

There is no guidance on when to use this versus extract_single_instrument, split_4stems, or other siblings, and no mention of prerequisites such as an uploaded file or credit consumption (cf. get_my_credits). The description is a label, not usage instruction.

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 behavioral context, but it only restates the extraction purpose and examples. It does not disclose permissions, processing behavior, whether the source is preserved, expected latency, or output/return characteristics.

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?

It is a single front-loaded sentence with no filler, so it is concise. The Quick Splitter label is mild branding rather than essential information, which keeps it from a perfect score.

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 4-parameter audio-extraction tool with no annotations, no output schema, and no schema descriptions, the definition is far too sparse. An agent lacks enough information to select it confidently or understand required inputs like source_key and kwargs.

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%, and the description mentions only instrument examples (guitar, piano). It leaves source_key, kwargs, and format unexplained, including the meaning of the required opaque kwargs parameter.

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

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

The description names a specific action (isolate) and target (a single instrument) with concrete examples (guitar, piano), so the agent can understand the operation without opening the schema. It does not explicitly distinguish this from sibling tools like split_4stems or extract_vocals, which keeps it below 5.

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?

There is no explicit when-to-use or when-not-to-use guidance, and no sibling alternative is named. The phrase Quick Splitter does not tell an agent whether to choose this over split_4stems or split_6stems for multi-stem separation.

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, yet it only reveals the output shape (two stems). It says nothing about whether this is an async job (siblings include check_task_status), credit consumption (get_my_credits), or that source_key must first come from get_upload_url.

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 short sentence with no filler, but it is under-specified rather than efficiently concise — the stem detail is front-loaded and useful, yet nothing else earns or fills the space.

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 three-parameter audio processing tool with no annotations, no output schema, and zero parameter documentation, one sentence cannot be complete. Missing workflow context (upload, async polling, credit cost) is material to calling it correctly.

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

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

Schema description coverage is 0% across three parameters, and the description mentions none of them. The opaque 'kwargs' parameter and the meaning of 'source_key' and 'format' are left 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?

States a specific verb ('Extract') and resource ('Vocals and Instrumental'), plus the output granularity ('2 Stems'). That implicit stem count distinguishes it from siblings like split_4stems and split_6stems, though no sibling is named explicitly.

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?

There is no guidance on when to choose this over split_4stems, split_6stems, or extract_single_instrument, nor any preconditions. The agent must infer selection purely from the stem count in the title-like phrase.

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. 'Check' implies a non-mutating read, which is helpful, but there is no disclosure of auth requirements, whether credits are user- or workspace-scoped, or whether the call has side effects 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?

A single front-loaded sentence with no filler or redundancy. 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?

For a trivial no-arg, read-only tool with no output schema, the description is nearly sufficient. The only minor gap is not indicating the shape of the credited value returned, though a credit count is largely self-evident from the phrase 'remaining credits'.

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

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

The tool takes zero parameters, so the baseline of 4 applies; there is no parameter semantics for the description to add or omit.

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?

States a specific verb ('Check') and resource ('current user's remaining credits'), so the agent knows exactly what it returns. The credit resource is distinct from every sibling (status checks, audio processing, uploads), though the description never explicitly contrasts itself with them.

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 no explicit when/when-not guidance or alternatives to consider. For a zero-parameter, obvious self-read the intended usage is implied, but nothing tells the agent to call this before e.g. submitting a credit-consuming job.

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 behavioral burden. It discloses the useful architectural fact that uploads go directly to R2 via a presigned URL, but omits URL expiry, accepted audio formats, any filename constraints, and whether the caller must follow up with upload_audio. Those are the traits that determine correct invocation.

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 tight sentence with the key mechanism front-loaded and no filler. It is appropriately sized, though brevity here partly reflects under-specification rather than economy.

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, no annotations, and a mutation-adjacent tool, yet the description does not say what the response contains (bare URL string, object key, expiry field) or how it connects to upload_audio. For this complexity level the definition leaves too much unstated.

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?

One parameter at 0% schema description coverage, so the description must compensate and does not. It says nothing about whether filename needs an extension, a specific format, a path prefix, or a uniqueness constraint.

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?

States a specific verb (get) and resource (a presigned upload URL) plus the mechanism and destination (direct to R2 storage). This is clear on its own, but it never names the closely related siblings upload_audio or submit_separation, so an agent must infer the sequencing between them.

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 statement of when to call this versus upload_audio, no prerequisites, and no ordering guidance. The existence of an upload_audio sibling makes the missing relationship the single most important thing an agent needs here, and it is absent.

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 behavioral burden. It implies a read-only listing but never states that it is safe/non-mutating, whether it requires authentication or credits (relevant given siblings like get_my_credits), or what the listing contains. Only the barest behavioral signal is 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?

A single compact sentence with the verb and resource front-loaded and no filler. It is efficient, though 'audio processing capabilities' is slightly abstract where 'tools' or 'operations' would be more concrete.

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?

With no output schema, the description should convey what the returned list actually contains (tool names, descriptions, parameter requirements), which it does not. For a zero-param discovery call the omissions are modest but real.

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

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

The tool takes zero parameters, so there is nothing for the description to clarify beyond what the empty schema already shows. Baseline for a no-param tool applies.

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?

States a clear verb ('List') and resource ('audio processing capabilities offered by SonicAura'), so an agent can tell this is a discovery/enumeration tool rather than an action tool like extract_vocals or submit_separation. It lacks explicit sibling differentiation, but no sibling performs capability listing, so the purpose reads unambiguously.

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 no when-to-use guidance, no prerequisites, and names no alternatives. An agent could infer it is a discovery call, but nothing states when this should be preferred over, say, check_service_status for probing availability.

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 the full behavioral burden. It discloses only the four output stem categories and says nothing about whether files are created, whether processing is asynchronous, whether credits are consumed, or what format the results take.

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 single sentence is front-loaded and contains no filler. Its brevity is efficient, though it is arguably too sparse for a tool with three undocumented parameters.

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

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

Given no annotations, no output schema, and 0% parameter description coverage, the description is far too thin. An agent knows it yields four stems but not how to provide the source, what kwargs means, or what format controls.

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 for all three parameters. It mentions none of them: not source_key, not kwargs, and not format, despite format defaulting to mp3 and kwargs being required.

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

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

The description states a specific action ('Split') and names the four resulting stems, so the core operation is clear. It does not explicitly differentiate itself from the sibling split_6stems, but the stated stem count and output list make the distinction readily inferable.

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?

There is no guidance on when to use this tool versus split_6stems, extract_vocals, or extract_single_instrument. It neither names alternatives nor states exclusions, leaving the agent to infer routing from the tool 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?

No annotations are provided, so the description carries the full behavioral burden, but it does not explain source requirements, processing behavior, async/task semantics, output format, or permissions. It only discloses the stem names.

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?

It is a single front-loaded sentence with no wasted words. However, the extreme terseness leaves important invocation details unstated.

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 three-parameter tool with no annotations and no output schema, the description is missing critical context about inputs, required kwargs, format behavior, and what the caller receives. Listing the six stems is useful but not 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 description coverage is 0% for all three parameters, including the required source_key and kwargs. The description does not explain any parameter, so it fails to compensate for the undocumented 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 a specific action and resource: splitting audio into six named stems. The list of stems distinguishes it somewhat from split_4stems and extract_vocals, though it does not explicitly name or contrast those 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 gives no guidance on when to choose this tool over split_4stems, extract_single_instrument, or extract_vocals. Usage is only implied by the six-stem output list.

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