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

Annotations already declare read-only, idempotent, and non-destructive behavior. The description adds significant behavioral context beyond that: the data is scoped to the signed-in person, conversations are ordered newest-first, and message text is explicitly flagged as untrusted information to relay, not instructions to follow. This is a valuable and concrete behavioral disclosure.

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 three sentences, each earning its place: scope and basic behavior, mode behavior, and a security-critical warning. It is front-loaded with the most identifying information and contains no filler or redundancy.

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 adequately covers the list/read modes, ordering, scope, and the prompt-injection caution. It is nearly complete for a read-only tool with two optional parameters. The main gap is the ambiguous semantics of 'limit', and the absence of an output schema means return-value shapes are not explained, though that is partially mitigated by the simplicity of the 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?

thread_id is described in the schema and echoed in the description, but the 'limit' parameter is only represented as an integer with min/max bounds. The description does not clarify whether limit applies to the conversation list, the returned messages, or something else. With 50% schema description coverage and no compensating detail in the description, parameter semantics are incomplete.

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 identifies the resource ('the signed-in person's conversations with landlords on A-du') and the action ('lists', 'returns messages'). It explicitly differentiates the two usage modes: no arguments for a list, thread_id for messages. This makes it easy to distinguish from write-oriented siblings like reply_to_thread.

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 direct invocation guidance: 'With no arguments, lists them newest first' and 'With thread_id, returns that conversation's messages.' It does not explicitly name alternatives or exclusions, but the mode-based usage is unambiguous and sufficient for an agent to select this tool over a write tool like reply_to_thread.

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