Computer-Use Agents API

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

With no annotations, description discloses idempotency (no-op on missing/finished sessions), a key behavioral trait. Missing details on side effects or permissions, but acceptable for simple 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?

Single sentence, front-loaded with action, no redundant words. Every word 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 1 parameter, no nested objects, and presence of output schema (which covers return info), description covers purpose, behavior, and prerequisites. No gaps.

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 description should compensate. It only implies session_id identifies the session, but does not explicitly describe its format or role beyond the parameter name.

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 clearly states verb 'Cancel' and resource 'session', and adds idempotency behavior distinguishing it from sibling tools like list_agents or send_message.

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?

Implicitly tells when to use (to end a session) and notes safe behavior ('no-op' if not exist or finished), but lacks explicit alternatives or when-not-to-use guidance.

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 for behavioral disclosure. It only states what is listed, but does not mention pagination, rate limits, auth requirements, or that the tool is idempotent. The name suggests a read operation, but this is implicit.

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 that immediately conveys the main purpose. It is concise but omits important details about parameters and behavior, making it somewhat incomplete.

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 the tool's low complexity and presence of an output schema, the description fails to mention pagination, which is critical for a list tool. It does not explain how the page and size parameters work or indicate that results are paginated.

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%, yet the description adds no explanation for the 'page' and 'size' parameters. It does not mention pagination or how these parameters affect the listing. The schema itself lacks parameter descriptions.

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 that the tool lists agents the caller can run, specifying 'their org's agents plus the public ``h/`` ones.' It uses a specific verb (list) and resource (agents), and distinguishes from sibling tools like 'run_agent'.

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 listing available agents, but does not explicitly state when to use or not to use this tool versus alternatives like 'run_agent' or 'cancel_session'. No exclusions or context cues 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 carries full burden. It mentions that the tool may return a session handle, hinting at asynchronous behavior, but does not disclose error handling, state changes, or permissions. The description is adequate but lacks depth for a potentially long-running 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?

The description is concise with two statements in one sentence. It is efficient and to the point, though the second statement is slightly cryptic ('``agent`` from list_agents') and could be integrated better.

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 has 5 parameters, a required task and agent, and an output schema (not shown), the description is incomplete. It does not explain the meaning or usage of optional parameters, nor does it describe the output schema or return format for the answer or session handle. Essential details for proper invocation are 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 input schema has 5 parameters with 0% description coverage (no schema descriptions). The description only explains 'task' and 'agent' implicitly ('Start an agent on a task' and 'agent from list_agents'), but does not explain 'max_steps', 'max_time_s', or 'idempotency_key'. Since schema coverage is 0%, the description fails to compensate.

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: starting an agent on a task and returning either the answer or a session handle. It also references 'agent from list_agents,' linking it to the sibling tool list_agents, which distinguishes it.

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 when to use the tool: to start an agent and get the answer or a session handle for later waiting. However, it does not explicitly exclude alternatives or give guidance on when not to use it, such as when a session already exists.

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 provided; description does not disclose effects on session, failure modes, or authorization needs. Only states the action without 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?

Single focused sentence with no redundancy. Front-loaded with action and resource.

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?

Adequate for a simple tool but lacks parameter descriptions, output details, and behavioral notes given no annotations.

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 has 0% coverage; description does not explain session_id source or message constraints. Fails to add meaning beyond property 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 verb 'Send', resource 'message', and context 'to a running session'. Distinguishes from siblings like cancel_session or list_agents.

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 usage for sending follow-up messages to running sessions, but no explicit when-not-to-use or alternatives 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?

With no annotations, the description carries full burden. It discloses the main effect (changing read permissions) and return value (share URL), but omits details like reversibility, permission requirements, 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?

One sentence clearly states the purpose and output, with no filler words. It is front-loaded and 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?

Despite having an output schema and one parameter, the description lacks essential context about parameter details and behavioral constraints (e.g., error conditions, idempotency), making it incomplete for reliable use.

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 single parameter, session_id, has no description in the schema (0% coverage) and the tool description adds no clarification about its format (e.g., UUID) or how to obtain it, forcing the agent to guess.

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 (make publicly readable) and resource (session), and distinguishes it from sibling tools like cancel_session and list_agents through its unique action of sharing.

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?

While the description implies when to use (to make a session shareable), it lacks explicit guidance on prerequisites (e.g., session ownership) or when not to use (e.g., if session is already public).

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 provided; description lacks details on side effects, idempotency, rate limits, or error behavior. For a polling tool, basic safety info is missing.

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?

Single sentence, concise, front-loaded with key verb and two modes. No unnecessary 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?

Adequate for a simple 2-param tool with output schema, but could mention return format or error cases. Not fully comprehensive.

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 has 0% description coverage, but the description clarifies the boolean 'wait' parameter's effect and 'session_id' is self-explanatory. Adds significant meaning beyond 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 it polls a session with two modes: long-poll for answer or return snapshot. Distinct from siblings like cancel_session or send_message.

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 wait vs non-wait but no explicit guidance on when to prefer this tool over alternatives or prerequisites.

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