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

No annotations are provided, so the description must disclose behavioral traits. It describes the action as non-mutating ('List'), which implies a read-only operation, but it does not explicitly state there are no side effects, nor does it mention authentication requirements, pagination, or output format. 'Including host capabilities' hints at extra data, but no details are given. This is adequate for a simple list tool but not richly transparent.

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 concise sentence that front-loads the primary purpose ('List Muster-owned sessions and tasks') before adding the secondary detail about host capabilities. It contains no filler or repetition, and its brevity is appropriate for a tool with only one optional parameter.

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 low complexity (one optional enum parameter, no output schema, no annotations), the description covers the main purpose but leaves gaps: it does not explain the 'kind' parameter's effect, nor does it describe the return structure. The phrase 'including host capabilities' suggests extra output but is undefined. For a simple list tool, this is moderately complete but not fully self-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?

The description does not explain the 'kind' parameter at all. The schema provides an optional enum of 'session' or 'task', but with 0% schema description coverage, the description should clarify how this parameter filters results. The overview says 'sessions and tasks' but not that 'kind' selects between them. This is a meaningful gap, as the parameter's role is left entirely to inference from the schema's enum values.

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 operation: 'List Muster-owned sessions and tasks'. It uses a specific verb ('List') and names the resource, which distinguishes it from siblings like 'run', 'stop', and 'output'. The additional 'including host capabilities' makes the scope more specific without confusing the core purpose.

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: the agent should call this when it needs to enumerate existing sessions/tasks. However, it does not explicitly state when to use it over alternatives (e.g., before running or stopping), nor does it describe when not to use it. There is no mention of prerequisites or routing to siblings, leaving the agent to infer the use case.

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 behavioral disclosure. It only says 'Read', implying a non-mutating operation, but does not state whether the task must be finished, whether it blocks, what happens if the id is invalid, or what the output format is. The description is too sparse to convey essential 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?

The description is a single short sentence, which is concise, but it is under-specified. It lacks essential context that should be present given the absence of annotations and parameter descriptions. The brevity works against the agent rather than aiding it, so it is not appropriately sized for the tool's needs.

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 one parameter, no annotations, and no output schema, the description is severely incomplete. It does not explain what the 'id' is, what 'captured output' means, how to obtain the output, or what the response will look like. An agent cannot reliably invoke this tool correctly based on the provided definition.

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 a single required parameter 'id' with no description, and schema coverage is 0%. The description does not explain what 'id' refers to (presumably a task run ID) or how to obtain it. The agent has no information about the parameter's meaning, format, or constraints beyond a minLength of 1.

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 'Read' and the resource 'captured output from a task run', which distinguishes it from sibling tools like run, list, and stop. However, it is slightly vague about what 'captured output' includes (e.g., stdout, stderr, logs), so it does not fully specify the resource.

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

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

The description provides no guidance on when to use this tool versus alternatives such as list or run. It does not mention prerequisites like the task needing to be completed, nor does it contrast with siblings. The agent is left to infer usage context.

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

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

With no annotations, the description carries the safety/behavior burden, and it does disclose a non-obvious trait: sessions return only when reachable, while tasks return a non-messageable run handle. However, it does not mention side effects, auth requirements beyond the schema's sandbox/permissions notes, or how the returned handle is consumed.

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 filler; the core action is front-loaded and the return-behavior nuance is compressed into the second sentence. 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?

With eight parameters, five enums, no output schema, and no annotations, two sentences leave too many operational gaps (defaults, host/runtime choice, handle consumption). The session/task distinction helps, but an agent still lacks enough to call this complex tool 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 only 25%, and the description compensates only for `kind` by defining session vs task return behavior. cwd, args, host, runtime, and prompt remain semantically unexplained in either the schema or the 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 uses a specific verb ('Launch') with a clear resource ('an instructed agent') and immediately defines a meaningful sub-distinction between sessions and tasks. This makes it easy to distinguish from the sibling management commands list, stop, and 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 the tool is for starting an agent and clarifies the session/task return contract, but it never states when run should be preferred over list/stop/output or gives exclusions/prerequisites. Usage context is inferable from the name and siblings, not explicit.

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

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

No annotations are provided, so the description carries full responsibility for behavioral disclosure. It only says 'Stop,' implying a mutating action, but does not disclose whether stopping is irreversible, what happens to the run's output, permission requirements, or idempotency.

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. Every part contributes: the action, the resource scope, and the accepted identifier forms.

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 tool is simple and the description covers the action and parameter semantics, so an agent can likely invoke it correctly. However, with no annotations and no output schema, it omits behavioral consequences and does not mention how to obtain the id or name, despite the sibling list tool existing.

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 one required string id with no description (0% coverage). The description adds crucial meaning by explaining that id can be a durable id or an unambiguous peer name, which is not derivable from the schema. It does not define the formats, but it compensates well for the schema gap.

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

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

Description uses a specific verb ('Stop') and names the exact resource ('Muster-owned run'), plus the identifier forms accepted. It is clearly distinct from siblings run, list, and 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 this tool is for stopping an existing Muster-owned run and even states how to identify it, but it does not explicitly mention when not to use it or direct the agent to list for finding ids. Usage context is clear but alternatives are left implicit.

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