MyClawn Computer

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the trailing 'Read-only.' adds little. What the description does add is behavioral scope beyond the annotations: it only covers the LATEST task (not history), and it reports both step detail and running state. That is useful disclosure, though nothing about freshness, staleness, or limits of the step list.

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 what is returned and backed by when-to-use conditions; nothing is buried. The only waste is the terminal 'Read-only.', which merely restates readOnlyHint=true already present in annotations.

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 an output schema present, the description need not describe return values, and with zero params there is no parameter burden, so the description is sufficient to invoke correctly. The remaining gap is sibling disambiguation against myclawn_desktop_status and myclawn_desktop_tasks, which an agent choosing between near-identical status-style tools would want resolved.

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 disambiguate; the baseline for a no-param tool applies. It correctly signals the scope is fixed to 'the latest task' rather than requiring any selector, which is the only semantic point worth noting.

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 concrete verb and resource ('Shows the latest task's steps on the MyClawn computer') and enumerates the content returned (pages opened, clicks, notes), plus a liveness check. It is clear on its own, but it does not differentiate itself from the closely related siblings myclawn_desktop_status and myclawn_desktop_tasks, which sound like they could also report task state.

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 gives explicit triggering conditions: checking a long task, following up after myclawn_desktop_run reported work in progress, or when the user asks how it is going. That is strong when-to-use guidance naming a sibling. It stops short of any when-not guidance or comparison against myclawn_desktop_status/tasks, which is the main ambiguity an agent would face.

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?

Beyond the annotations (destructiveHint=true, idempotentHint=true), it discloses the crucial partial-execution semantics: the task stops at its current step and already-completed actions such as a sent email or submitted form are not undone. It also explains the no-op behavior when nothing is running and the resulting 'interrupted is false', which tells the agent how to interpret the outcome.

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 short sentences, front-loaded with what the tool does, then when to use it, then the state caveats. Every sentence adds distinct decision-relevant information with no repetition of the title or annotations.

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 zero-parameter interrupt with an output schema, the description covers purpose, trigger conditions, irreversible side effects, and the null case. An agent has everything needed to decide whether to call it and how to read the result.

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; the schema baseline of 4 applies. No parameter claims are made that could mislead.

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 verb and resource: stop the task the MyClawn computer is running right now. It implicitly separates this from list-oriented siblings like myclawn_desktop_tasks and myclawn_desktop_status, but it never names a sibling or draws an explicit boundary, so it falls 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?

It gives clear triggering conditions ('when the user asks to stop, or a task is clearly going wrong') and notes the harmless case where nothing is running. It does not name any alternative tool or describe when not to call it, so it stops short of the explicit routing a 5 requires.

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?

Annotations already declare destructiveHint=true and openWorldHint=true, but the description adds genuine behavioral context beyond them: the returned agent answer plus replay_url recording, multi-minute runtimes, persistent browser sign-in between jobs, and consumption of the user's MyClawn plan. It does not clarify reversibility or failure/partial-completion behavior for a destructive open-world action, keeping it from a 5.

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 definition is front-loaded with what the tool is, then moves to usage and return behavior. Every sentence carries information, though the dense enumeration of use cases makes it longer than strictly necessary for an experienced agent.

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?

An output schema exists, yet the description still surfaces the user-facing replay_url and the multi-minute latency that an agent must communicate. Combined with the message-briefing guidance and plan-usage note, nothing an agent needs to select and invoke this tool correctly is missing.

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 100%, so the schema already documents both parameters, establishing a baseline of 3. The description does add briefing guidance for 'message' ('write the task the way you would brief a contractor ... include only what the task needs, not the conversation'), but the 'private' parameter is never mentioned in the description text, so value beyond the schema is marginal.

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 verb and resource ('Hand a job to the user's own MyClawn computer'), which is far more than a restatement of the name. It enumerates concrete job types (signed-in browsing, email, forms, file editing, long-running tasks), making the capability unambiguous. It does not, however, explicitly differentiate itself from the sibling read/utility tools (activity, status, tasks), 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?

It gives clear when-to-use guidance: 'Use it for what you cannot do from this chat', followed by specific scenarios. This establishes a positive selection rule and an implicit exclusion (things doable from chat). It does not name alternative sibling tools or state when another tool would be preferable, so no explicit alternative routing is present.

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?

Goes well beyond the annotations: same-name files are replaced, text only, 2 MB cap, returns saved name and path, and the no_machine state when the user has no computer. The overwrite/2 MB/no_machine details are behaviors the annotations and schema do not convey, giving the agent real operational 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?

Four tight sentences, front-loaded with the action and path, then the usage rationale, then constraints, then return/edge state. No filler and every clause carries 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?

An output schema exists, yet the description still supplies what matters for correct invocation: size/type limits, overwrite semantics, and the no_machine failure state. Nothing an agent needs to call or interpret this tool is missing.

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 100%, so both parameters (name, content) are already fully documented, including the sanitization rule and 2 MB limit. The description echoes the text-only/2 MB constraint and the 'refer to the file by name' usage, adding only marginal meaning beyond the schema, so baseline 3 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 concrete verb (puts/writes) plus the exact resource and destination path (/home/user/Desktop) and the reason the agent would want it (so its agent can read/use it). It is clearly distinguishable from the run/interrupt/status siblings, which do not place 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 says when to use it ('instead of pasting long text into a task') and describes the downstream workflow ('refer to the file by name in the task'). It names an alternative behavior rather than a named sibling, so it stops short of a full routing table, but the context is unambiguous.

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?

Annotations already cover readOnly/idempotent/non-destructive, so the bar is lower; the description adds real value by disclosing data provenance (server's copy, not a local record) and the failure modes encoded in state: 'no_machine' and 'unavailable ... the mail copy could not be read just now.' It omits pagination or ordering behavior, but the output schema presumably covers shape.

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?

Front-loads what it does, then the use case, then the behavioral qualifiers. Every clause earns its place: provenance, returned fields, purpose, and failure states. No padding or repetition.

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 an output schema present, the description needn't detail return values, and it already names the key fields and the state outcomes. Combined with rich annotations and a zero-parameter schema, an agent has everything needed to select and call 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?

The tool takes zero parameters, so the baseline of 4 applies. The description correctly does not invent parameter semantics, and the state enumeration reflects the response rather than an input.

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 ('Lists') and resource ('every email the MyClawn computer sent from its own address'), plus the exact provenance ('read from the mail server's copy') and the returned fields (recipient, subject, time). This is clearly distinguishable from siblings like send_file, activity, or tasks, which serve different resources.

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?

Gives two concrete use cases: 'confirm a message really went out' and 'show the user what was sent.' That is clear contextual guidance. It doesn't name an alternative tool or an explicit when-not-to-use, but no sibling appears to be a competing read path for sent mail.

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?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds genuinely useful behavior the annotations do not: fields are null when there is no plan or computer yet, which tells the agent how to interpret an empty response.

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 tight sentences ordered as payload, trigger, and edge-case caveat. Nothing is repeated from the title or annotations, and 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 no-arg read-only status tool with an output schema, the description covers what is returned, when to call it, and how to read null fields. No return-format explanation is needed since the output schema carries that, so nothing an agent needs is missing.

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 to mis-specify; the schema is trivially complete. The description correctly adds no parameter chatter, which is the right choice for a no-arg tool.

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?

Names a specific verb+resource and enumerates exactly what is returned: plan, free trial with hours left, computer readiness, and the computer's email. This distinguishes it clearly from siblings like myclawn_desktop_activity or myclawn_desktop_tasks, which report different data about the same computer.

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?

Gives two concrete trigger conditions: when the user asks about their MyClawn setup, or after a task reports the computer is still starting. It does not name alternative tools to prefer, but the triggers are specific enough to select this tool reliably.

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?

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the description is not carrying that burden. It adds genuine value beyond them by disclosing ordering (newest first) and the edge case of an empty list when the computer is not set up or running.

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 tight sentences with purpose and ordering front-loaded, followed by usage and then the edge case. Every sentence carries distinct information and nothing is redundant.

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 read-only, zero-parameter listing tool with an output schema and full annotation coverage, this covers purpose, trigger, ordering, and the empty-list edge case. An agent has everything needed to select and call it; the output schema handles 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?

The tool takes zero parameters and schema coverage is 100%, so there is nothing for the description to compensate for; the 0-parameter baseline applies. There is no filtering or pagination parameter to explain.

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 ('Lists the tasks the MyClawn computer has run') plus ordering ('newest first') and the returned fields. It conceptually separates itself from activity/status siblings, but never names an alternative tool, so the distinction is inferred rather than 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?

Gives a clear trigger: 'Use it when the user asks what the computer did earlier or whether a job finished.' That is actionable context, but there are no exclusions and no routing to myclawn_desktop_activity or myclawn_desktop_status, which look adjacent.

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?

Annotations already establish readOnlyHint=true, idempotentHint=true, destructiveHint=false, and a closed world, so the safety profile is covered. The description adds genuinely useful behavioral detail beyond that: a capped result count of 5, best-match-first ordering, and an empty list on no match. The 'Read-only' sentence merely restates the annotation.

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 definition is two tight sentences that lead with the core action and result behavior, followed by the usage condition. Every sentence carries weight except the trailing 'Read-only.', which duplicates the readOnlyHint annotation and could be dropped.

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 single-parameter retrieval tool with 100% schema coverage and an output schema, the description supplies everything an agent needs: the matching semantics, the result cap and ordering, the empty-result case, and the usage trigger. Nothing material is missing.

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 100%, so the schema already documents the single query parameter and its examples. The description adds interpretive meaning beyond the schema by clarifying the matching model: results 'share a word with the search,' i.e. word-overlap matching rather than substring or fuzzy search. That is a real, non-duplicative clarification.

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 verb and resource (searches notes saved in MyClawn memory) plus the mechanism (by keyword), and states the result shape (up to 5, best match first). It is clearly the read counterpart to the sibling myclawn_notes_remember, so an agent can tell them apart without opening either schema.

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 gives an explicit trigger condition: 'Use it when the user refers to something they asked you to remember.' That is clear context for selection. It stops short of naming the alternative (myclawn_notes_remember) or stating when NOT to use it, so it is not a full when/when-not/alternatives treatment.

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?

Annotations only declare the safety profile (readOnly=false, destructive=false, openWorld=false, idempotent=false). The description adds a real behavioral trait beyond them: the note becomes visible to the user's MyClawn computer and every connected assistant, i.e. shared persistent state. It does not address what happens on a repeated save despite idempotentHint=false.

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 tight sentences: what it does, when to call it, when not to. The trigger condition is front-loaded and every sentence carries distinct 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?

An output schema exists, so return values need no explanation, and the two parameters are fully covered by the schema. The description covers purpose, trigger, and visibility scope; only repeated-save/duplicate behavior is unaddressed for a non-idempotent write.

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 100%, with the 'kind' enum values and the 'text' one-sentence/500-char constraint already documented in the schema. The description adds no parameter guidance at all, so the baseline 3 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 specific verb and resource ('Save a note to the user's MyClawn memory') and immediately scopes it to shared/global memory. It is clearly distinguishable from the sibling myclawn_notes_recall, which reads notes back.

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?

Explicit when-to-use ('Only when the user asks you to keep something ("remember that…")') plus an explicit exclusion ('Never save conversation content on your own'). Nothing about invocation timing is left to inference.

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