Sonnet 5 Agent

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint. The description supplements these by noting the tool does not run the model and requires no token, adding context beyond annotations without contradiction.

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: first states the result, second clarifies usage. No wasted words; 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 simple, parameter-less metadata tool with comprehensive annotations and a clear sibling set, the description fully covers purpose, behavior, and prerequisites (no token needed). Output schema absence is not a gap since return value domain is described.

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?

With zero parameters and 100% schema coverage, the description adds crucial meaning by explaining what the tool returns (identity, price, endpoint, URL), which is not evident from the empty 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 uses a specific verb ('Returns') and lists the exact resources (identity, price, endpoint, URL), clearly distinguishing this metadata tool from sibling tools like agentfarm_create_run that execute model runs.

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 states 'This metadata call does not run the model and does not require a bearer token', which tells the agent when to use this tool (to get info) and when not (for running models), and clarifies authentication requirements.

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, idempotentHint=true, and readOnlyHint=false; the description adds the state limitation and an authentication qualifier beyond the annotations. It does not detail side effects such as whether execution is stopped immediately, but with annotations covering destructiveness this is reasonably 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?

One short sentence with no filler, front-loading the action and target. Every word adds clarity, and it is appropriate for a single-parameter cancellation 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?

For a simple cancel operation with one well-documented parameter and annotations declaring idempotence and destructiveness, the description plus schema is nearly complete. A minor gap is that the description does not indicate what result or state change to expect after cancellation.

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 fully documents the single parameter run_id as 'AgentFarm run identifier' (100% coverage). The description adds no parameter-level meaning beyond the schema, so the baseline score of 3 is appropriate.

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 ('Cancels') with a clear resource ('AgentFarm run') and adds state scope ('queued or running'), making the action unambiguous. This distinguishes it immediately from sibling read/create tools like agentfarm_get_run_status and agentfarm_create_run.

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 phrase 'authenticated queued or running run' gives a clear precondition: only runs in those states are valid cancellation targets. It does not explicitly name alternatives or list when not to use it, but the verb and sibling set make the appropriate context obvious.

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?

The description discloses meaningful behavioral traits beyond the annotations: the task is asynchronous ('Queues'), requires authentication ('authenticated'), and can consume paid model capacity. These are significant facts an agent needs before invoking the tool, and none of them are present in the annotation booleans.

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, purposeful sentences: the first states the core action, the second warns about cost, and the third gives the follow-up workflow. There is no filler or redundant restating of the schema.

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 is largely complete: it explains the async behavior, cost implications, and the correct next steps. The only gap is that it does not explicitly state what the create call returns (e.g., a run ID needed for polling), though that is reasonably implied by the polling instruction.

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 task, task_input, and idempotency_key. The description adds no additional parameter-level detail, but it is not required to compensate because the schema fully covers parameter semantics.

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, 'Queues', and a clear resource, 'an authenticated asynchronous task', which matches the title 'Create a Sonnet 5 Agent run'. This clearly differentiates it from siblings like agentfarm_get_run_status, agentfarm_get_run_result, and agentfarm_cancel_run, which are all read or lifecycle operations.

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 a clear workflow: create the run, poll with agentfarm_get_run_status, then read with agentfarm_get_run_result. It does not explicitly state 'use this instead of X' or list when-not-to-use conditions, but the workflow context makes the intended usage 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 declare readOnlyHint, destructiveHint, idempotentHint; description adds only the authentication requirement, which is minimal behavioral context beyond annotations.

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 with no extraneous words; front-loaded and direct.

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 retrieval tool with one parameter, good annotations, and no output schema; could mention timing (call after run completes) but not essential.

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%; description adds no additional meaning to the run_id parameter beyond what's in the 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 the tool returns final summary and artifact download URLs for a run, which is specific and distinguishes it from sibling tools like get_run_status or create_run.

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 explicit guidance on when to use this tool versus alternatives (e.g., after run completion). The mention of 'authenticated run' provides context but not comparative usage.

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 readOnly and idempotent hints. Description adds value by enumerating the four possible status values (queued, running, succeeded, failed) and noting 'authenticated run', implying authentication requirements.

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 the key information (returned statuses). No wasted 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?

No output schema, but description adequately hints at return values. With only one parameter, the tool is simple enough that no further detail is needed.

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 100% with a clear description of run_id. Description adds 'authenticated' context but no further parameter semantics beyond the 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?

Description clearly states it returns the status of a run, listing the possible values (queued, running, succeeded, failed). This distinguishes it from sibling tools like agentfarm_create_run or agentfarm_get_run_result.

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?

Impiles usage for checking run status but does not explicitly guide when to use this tool versus alternatives like agentfarm_get_run_result. No exclusion criteria or context provided.

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