Fable 5 Agent

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

Annotations already provide readOnlyHint, destructiveHint, idempotentHint. Description adds context beyond annotations: 'does not run the model' and 'does not require a bearer token.' This enriches the behavioral profile.

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 the core action. Every sentence adds value; no redundancy or filler.

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 no output schema, description lists all return values explicitly. Tool is simple; this is sufficient. Could mention price unit, but not necessary.

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?

No parameters in schema, so baseline is 4. Description adds meaning by listing returned fields (identity, price, endpoint, URL), compensating for lack of output 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 specific verbs and resources: 'Returns this agent's identity, listed per-task price, MCP endpoint, and access URL.' It clearly distinguishes from siblings (create run, get run result, get run status) by stating it is metadata, not a run operation.

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 explicitly states when to use: when you need agent info without running the model, and it does not require a bearer token. It implies not to use when you need to run a model, which differentiates from sibling tools.

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 idempotentHint=true, covering the safety profile. The description adds useful context by restricting cancellation to queued or running runs, but does not disclose side effects such as whether results become unavailable or whether cancellation is reversible. This adds a similar level of value as the calibration example where annotations carried the safety burden.

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 sentence with no filler words. The core action, resource, and state constraint are all conveyed efficiently, and nothing needs to be trimmed.

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 one-parameter tool with annotations covering destructiveness and idempotence, this description is nearly complete. It covers what the tool does and the applicable run states. It could mention handling of completed or nonexistent runs, but that is a minor gap for such a simple operation.

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 single run_id parameter is already documented as an 'AgentFarm run identifier.' The description adds no additional parameter semantics beyond implying the run must be queued or running, so the baseline score of 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?

The description states a clear verb (Cancels) and resource (queued or running run), which distinguishes it from sibling tools like create_run, get_run_status, and get_run_result. The phrasing 'authenticated queued or running' adds scope but is slightly ambiguous about whether it refers to runs belonging to the authenticated user or runs with authentication 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?

The description implies when to use the tool — when a queued or running run needs to be stopped — but does not explicitly mention when not to use it or reference alternative tools. The state restriction (queued or running) provides useful context, but exclusions are left to inference.

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 adds meaningful behavioral context beyond the annotations: the task is asynchronous, requires authentication, and can consume paid model capacity. This is especially valuable for a mutation-like operation where cost and async behavior are critical for agent decision-making. No contradiction with 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?

The description is two concise sentences with no filler. It front-loads the core action, then adds a critical cost warning and a clear follow-up path. 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 tool with no output schema, the description adequately explains the full lifecycle: creation, polling, and result retrieval. It also surfaces the cost and auth requirements in one short description. Combined with the complete parameter schema, the agent has everything needed to call this tool 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 input schema has 100% parameter description coverage, so the baseline is 3. The description itself does not add parameter-level detail beyond what the schema already provides, but the schema already sufficiently documents 'task', 'task_input', and 'idempotency_key'.

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 resource ('an authenticated asynchronous task'), clearly identifying the tool as the creation/queueing step. It also implicitly distinguishes from sibling tools by referencing the follow-up status and result tools, so an agent understands this is not the poll or read operation.

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 clearly states the intended workflow: queue a task, then poll with agentfarm_get_run_status, then read agentfarm_get_run_result. This gives clear context on when to use this tool relative to its siblings. It does not explicitly state when not to use it or mention alternative creation methods, but the workflow guidance is strong.

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=true, idempotentHint=true, destructiveHint=false. The description adds value by specifying that authentication is required and what the return includes (final summary, artifact URLs). No contradictions.

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, dense sentence that front-loads the primary action and key outputs. No redundant words or fluff.

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 one required parameter, full schema coverage, and annotations, the description adequately covers the tool's purpose and output. However, lacking an output schema, it could mention the structure of the 'final summary' or format of artifact URLs.

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% and the parameter description ('AgentFarm run identifier.') is sufficient. The tool description does not add additional detail beyond what the schema provides, so baseline of 3.

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 specifies the verb ('Returns'), the output ('final summary and artifact download URLs'), and a condition ('authenticated run'). It clearly distinguishes from siblings like agentfarm_get_run_status (status) and agentfarm_create_run (creation).

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 'final summary' implies use after a run completes, but the description does not explicitly state when to use this vs. siblings like agentfarm_get_run_status. However, the sibling names provide enough context for an AI to infer.

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, idempotentHint, and destructiveHint, so the description adds limited behavioral context (returns status values). It mentions 'authenticated run' but does not elaborate on error handling or side effects beyond what annotations cover.

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 sentence conveys all essential information without waste. It is front-loaded with the key verb and result types.

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 status check with one required parameter and no output schema, the description covers the bare minimum. However, it lacks details about the return format, potential error cases, or additional fields (e.g., timestamps). Slightly incomplete given the lack of an output schema.

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 run_id described as 'AgentFarm run identifier.' The description adds no extra parameter meaning; it only mentions 'authenticated run' which is context but not parameter-specific. 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?

The description clearly states it returns one of four statuses (queued, running, succeeded, failed) for an authenticated run. It specifies the resource (run) and verb (get status), and distinguishes from siblings like agentfarm_get_run_result 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 description implies usage for checking run progress but does not explicitly state when to use this tool versus siblings (e.g., agentfarm_get_run_result for results). No guidance on prerequisites or exclusions is provided.

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