readMessages

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

The description goes well beyond the destructiveHint annotation by explaining exactly what is destructive: the buffer is cleared by default, and clearAfterRead=false preserves it. It also discloses the status return field for connection health, giving the agent a clear behavioral model 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?

Three concise sentences, each earning its place: first states the purpose, second explains the default destructive behavior and how to avoid it, third adds limit and return-value nuance. The most important information is front-loaded.

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 there is no output schema, the description usefully mentions the status field but does not describe the full shape of the returned messages array. Still, for tool selection and invocation the essential behaviors—buffer clearing, limit, retention, and connection status—are covered, leaving only minor ambiguity about response formatting.

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 description does not need to compensate for undocumented parameters. It does add a little context around limit ('recent N messages') and the default clear behavior, but these largely restate what the schema already declares, so the baseline 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 opens with a specific verb and resource: '读取指定订阅已积累的消息' (read messages accumulated for a specified subscription). It also immediately disambiguates from subscription-starting tools by focusing on consuming buffered messages, and adds the key default behavior (clearing the buffer).

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 usage context is implied rather than explicit: an agent can infer this tool is for consuming messages from an existing subscription, especially since subscriptionId is described as coming from startSubscription. However, the description does not explicitly state when to use this versus alternatives, nor does it mention exclusions like 'do not use if you want to keep the connection open without consuming messages.'

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