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

With no annotations provided, the description carries the behavioral burden, and it does disclose the key trait: the operation returns immediately with a job id rather than blocking for results. It stops short of mentioning side effects like stem files being written to disk, but the immediate-return behavior is the most important thing an agent needs to know.

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 short sentences with no filler. It front-loads the action and immediately gives the crucial return behavior, so every sentence earns its place.

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

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

For a moderately complex async tool with no output schema, the description is largely complete: it names the input, the expected stem outputs, and the immediate job-id return. It would be slightly richer if it pointed to stem_job_status for tracking, but the sibling names and schema defaults cover most remaining needs.

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 67%, so the schema already documents path, out_dir, and quality. The description adds no parameter-level meaning beyond the idea that the audio file is split into stems; model and backend remain explained only through enums/defaults. This is adequate but not compensatory.

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 ('Start separating'), identifies the resource ('one audio file'), and states the concrete outputs ('vocals / drums / bass / other'). It also distinguishes this launcher tool from sibling status/cancel/backends tools by noting it returns a job id immediately.

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 phrasing 'Start separating' and 'Returns a job id immediately' clearly frame this as the async job-launching tool, implying that stem_job_status should be used afterward. It gives clear context but does not explicitly say 'use stem_job_status to monitor' or 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?

With no annotations, the description carries the full burden of conveying behavior. 'Which ... this machine has' suggests a read-only informational query, and 'how to enable them' suggests the tool reports enablement guidance rather than mutating configuration. However, it is not explicit about whether the tool modifies anything or only returns information.

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

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

The description is a single sentence with no filler, and the core subject ('separation backends on this machine') is front-loaded. Every clause adds useful 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?

The description provides enough context for an agent to select the tool: it reports available backend types and enablement guidance, and there are no input parameters to prepare. It could be slightly clearer about whether the response contains instructions or the tool itself performs enablement, but this is a minor gap for a zero-parameter informational 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 input schema has zero parameters, so there are no parameter semantics for the description to clarify. This matches the baseline for parameterless tools.

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

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

The description clearly identifies the resource (separation backends on this machine) and the topic (which backends are available and how to enable them), even naming the two backend types. It is distinguishable from siblings like separate_stems or stem_job_status, though it lacks an explicit verb like 'list' or '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 purpose implies this should be checked before or alongside running stem separation, but the description never explicitly says when to use it versus the sibling tools. There is no when/when-not guidance or mention of alternatives.

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

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

With no annotations, the description carries the full burden and does disclose the key destructive trait beyond the name: it removes half-written stems, not just stops the process. However, it omits other behavioral context such as whether the action is reversible, what state the job record ends in, and what happens if the job is already finished or failed.

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 zero filler. 'Stop a running separation and remove its half-written stems' delivers the action and the cleanup side effect in under ten words, and every element 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 destructive mutation tool with no annotations, no output schema, and 0% parameter coverage, the description is too thin. It captures the core action but lacks prerequisites (job must be running), post-conditions, the role of job_dir, and any sense of the return value or error behavior.

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

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

Schema description coverage is 0%, so the description must compensate for the undocumented parameters. It does not clarify what job_id refers to beyond context, and job_dir (an optional parameter) is entirely unexplained, leaving an agent to guess its purpose and whether it must match a value from a status 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 uses specific verbs ('Stop', 'remove') with concrete resources ('a running separation', 'its half-written stems'), clearly identifying this as a job-cancellation and cleanup operation. It is readily distinguished from the siblings: separate_stems (creation), stem_job_status (monitoring), and stem_backends (listing), even though no sibling is named.

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?

Usage is implied: use this when a separation is running and you want to stop it. However, there is no explicit guidance about when NOT to use it (e.g., if the job already completed), no prerequisites (e.g., verifying the job is running via stem_job_status first), and no mention of alternatives.

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

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

With no annotations provided, the description carries the burden of behavior disclosure. It explicitly states this is a read operation and lists the returned aspects (status, stage, stems, errors), making the non-mutating nature and primary output clear. It does not describe edge cases like ordering or failure behavior, but it is reasonably transparent for a status-read tool.

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

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

The description is a single compact sentence that front-loads the verb and resource, then lists the returned fields. Every word earns its place, and it is not padded with schema-redundant material.

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 read tool with no output schema or annotations, the description gives the essential purpose, output areas, and parameter omission behavior. However, it leaves job_dir undefined and does not cover return formatting or behavior for missing/invalid jobs, leaving a moderate gap in complete guidance.

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 documents job_id ('Omit to list the recent jobs') but leaves job_dir entirely undocumented, and schema description coverage is only 50%. The description does not explain job_dir or how it relates to job_id, so an agent would not know how to use that parameter correctly.

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 the specific verb 'Read' and names the resource ('one separation job' or recent ones), plus the data returned: status, stage, stems, errors. This clearly distinguishes it from sibling tools like stem_job_cancel (cancel) and separate_stems (create), which have different purposes.

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 conveys when to use the tool: to inspect a separation job's status or list recent jobs. The schema's job_id description adds the key usage distinction ('Omit to list the recent jobs'), providing clear context. However, it does not explicitly mention exclusions or alternatives such as stem_backends or stem_job_cancel.

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