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

No annotations are provided, so the description carries the full burden. It does disclose that a result is returned only once the task is complete, which is genuinely useful, but it says nothing about what status values exist, whether the call is a safe read, or what happens for an unknown or expired task_id.

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 short sentences, front-loaded with the action and followed by the return semantics. There is no filler and nothing could be cut without losing 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?

For a single-parameter, non-mutating tool with no output schema, the definition is close to adequate: it signals the result is conditional on completion. It is still thin on the polling-versus-blocking decision and on the status domain, which an agent needs to act on the response.

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%, so the sole parameter is documented in the schema itself, which sets the baseline at 3. The description adds no parameter detail, and it does not resolve the naming mismatch between the 'task_id' parameter and the schema text calling it 'the intent_id returned by dispatch_task'.

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 ('Check status of a previously dispatched task') and adds the return behavior ('status and result if complete'). However, it never distinguishes itself from the sibling wait_for_result, which is the primary alternative an agent must choose between for the same 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?

Usage is only implied by the phrase 'previously dispatched task', which suggests calling it after dispatch_task. There is no explicit statement of when to poll with this tool versus blocking with wait_for_result, and no mention of polling cadence or when to give up.

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 and does well: it discloses asynchronous execution, an immediate return with an intent_id rather than the result, and the escrow-like payment rule (paid only after the result passes checks). It omits failure/timeout behavior and what happens to the budget if the task is never settled, which are meaningful gaps for a payment-bearing mutation.

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, each earning its place: what it does and the payment model first, then the async/immediate-return behavior, then where to go for the result. No repetition 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?

There is no output schema, and the description correctly compensates by explaining the return value (intent_id) and that the real output arrives later via sibling tools. For a 4-param tool with a nested input_data object, the remaining gap is failure/refund semantics rather than anything blocking a correct call.

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 all four parameters (capability, input_data, budget_usdc, description) are already documented in structured form; baseline is 3. The description adds indirect meaning about the payment contract that contextualizes budget_usdc, but gives no further detail on capability naming or input_data shape 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?

States a specific verb and resource (submit a task to THE LINE Protocol) plus the distinguishing mechanism: a verified agent executes and is paid only on passing checks. This is clearly separated from the sibling retrieval tools, so an agent can tell it apart without opening the 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?

Explicitly routes the agent downstream: 'Use check_task_status() or wait_for_result() to retrieve the output once an agent settles it', naming both siblings and the condition that selects them. It does not cover when not to dispatch (e.g., pre-existing tasks, choosing an agent via list_agents first) or how to size the budget, so it stops short of full when/when-not coverage.

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 the full burden. It discloses that the statistics are 'Live', which adds useful freshness context beyond the schema, and the zero-parameter schema makes mutation impossible. However, it does not explicitly state read-only behavior, authentication needs, rate limits, or whether the data is cached or aggregated.

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 front-loaded fragment with no filler. It could be slightly improved by clarifying the time window or output shape, but every word 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 zero-parameter stats tool with no output schema and no annotations, the description gives a useful enumeration of metrics but omits the time window, aggregation level, and return format. It is minimally adequate but leaves gaps an agent might need to resolve before calling.

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?

There are zero parameters, so the baseline is 4. The description correctly does not waste space discussing parameters and instead describes the returned metric categories.

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 resource (protocol statistics) and enumerates the metrics returned (agents, intents, transactions, volume, success rate). This clearly distinguishes it from sibling tools like dispatch_task and list_agents, though the term 'protocol' is left undefined.

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 guidance is given on when to use this tool, when not to use it, or what alternatives exist. The agent must infer that this is the monitoring/observability counterpart to the task-oriented siblings.

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 the full behavioral burden. 'List' implies a read operation and 'currently online' indicates a live-state scope, but the description omits permissions, rate limits, pagination behavior, and whether results are sorted or limited beyond the schema's limit parameter.

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 brief sentences, front-loaded with the core action and scope. There is no redundant wording or unnecessary detail.

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 list tool with two fully documented parameters and no output schema, the description is minimally adequate. However, with no annotations and no output schema, it should say more about return shape, ordering, and whether pagination applies.

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 limit and capability are already documented in the schema. The description mentions the capability filter but adds no extra semantics beyond the schema, and it does not discuss the limit parameter. Baseline 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?

States a specific verb and resource: 'List provider agents currently online on THE LINE.' The optional capability filter adds scope. It does not explicitly distinguish itself from siblings, but the purpose is unambiguous.

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 by saying it lists currently online agents and can optionally filter by capability. It does not explain when to use this versus siblings like dispatch_task or check_task_status, or any prerequisites.

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 must carry the full behavioral burden. It usefully discloses the 2-second polling interval and the terminal state set, but says nothing about what happens on timeout expiry (error vs partial result), whether the call blocks a shared connection, or what it returns.

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 short sentences, front-loaded with the blocking semantics and the termination conditions. 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?

There is no output schema, so the description should explain what the caller receives: the final task object, an error on timeout, or the current state. That return contract is absent, which is a meaningful gap for a wait-style tool.

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%, so both parameters are fully documented, including the default timeout of 300s and the intent_id provenance. The description adds no parameter detail beyond that, 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 specific verb+resource ('Block until a task reaches a terminal state') and enumerates the terminal states (settled/failed/refunded/cancelled). The word 'Block' implicitly separates it from check_task_status, but no sibling is named, so differentiation is left to inference.

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?

Usage is implied: use this when you want to wait rather than poll. There is no explicit guidance on when to prefer check_task_status (e.g. for long-running tasks or when you need intermediate progress) or on prerequisites such as having an intent_id from dispatch_task.

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