AgentAddress

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

With no annotations, the description carries full responsibility for behavioral disclosure. It only says the event is marked as handled, but does not explain effects on the queue, idempotency, required permissions, what read_token is for, or failure behavior. This is a significant gap for a state-changing 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 a single, front-loaded sentence with no fluff. However, it is under-specified for a tool with three required parameters and no annotations; brevity comes at the cost of missing necessary behavioral and parameter context.

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 no output schema, no annotations, and no parameter descriptions, the tool definition is incomplete. The agent is left without the meaning of read_token, the distinction between address_id and event_id, the effect of acknowledgment, or what response to expect.

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 0% and the description adds no meaning for any parameter. The raw parameter names suggest some purpose, but the description does not explain address_id, event_id, or especially read_token, nor how they relate to each other.

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 ('Mark') and a specific resource ('a queued event') with a clear outcome ('as handled'). The action is distinct from sibling tools like poll_events or create_return_address, so an agent can tell what this tool does even without extra context.

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 'queued event' implies this tool is used after handling an event, but there is no explicit when-to-use, when-not-to-use, or alternative guidance. It offers implied usage context rather than explicit routing among 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?

With no annotations provided, the description carries the full transparency burden. It usefully discloses durability and the critical one-time display of read_token. It does not cover permissions, side effects, or expiration behavior, but the token warning is meaningful and non-obvious.

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 with no filler. The primary action is front-loaded, and the one-time token warning is a high-value addition that 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?

The description explains what is created and warns about read_token, but there is no output schema and no mention of the result shape beyond the token. It also does not explain how the created resources connect to the sibling tools, leaving some operational context 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 67%, and the description adds no parameter-level meaning. It does not clarify expires_in_seconds, which lacks a schema description, and does not connect name or task_id to the creation behavior. The read_token warning is about output, not parameters.

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 a specific creation action with concrete resources: durable inbox, HTTPS callback URL, and event queue. It is immediately distinguishable from the sibling event-consumption tools acknowledge_event and poll_events.

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 tool's purpose implies it is the setup step before polling or acknowledging events, but the description never explicitly says when to use it versus the siblings. No alternatives or exclusions are mentioned, so usage context is only implied.

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. It discloses that the read token authenticates access and that this is a read operation, implying non-destructive behavior. However, it does not state whether polling advances the cursor, whether events remain queued until acknowledged, or any rate-limit or permission details, leaving important behavioral aspects unclear.

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 core action. Every word earns its place, and the critical qualifier about the read token is included without padding.

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 tool has four parameters, no annotations, and no output schema, yet the description is minimal. It leaves 'address_id' and 'limit' under-explained, omits polling lifecycle context (e.g., events persist until acknowledged), and does not discuss errors or edge cases. An agent would likely need to infer too much to invoke 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?

Schema description coverage is 0%, so the description must compensate. It explains 'after' as a cursor and 'read_token' as an authenticating credential, but it does not clarify the role of 'address_id' or the pagination semantics of 'limit' beyond the schema's min/default/max. This is partial compensation for a four-parameter 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?

The description states a specific action and resource: 'Read queued events after a cursor,' matching the title 'Poll return-address events.' The verb 'read' clearly differentiates from siblings 'acknowledge_event' and 'create_return_address,' so an agent can tell the tools apart.

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 polling versus acknowledging or creating. The description implies the tool is for reading queued events, but it never explicitly states when to choose this over sibling tools, nor does it mention prerequisites like needing an existing return address.

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