read_messages

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

Without annotations, the description carries the burden of behavioral disclosure. It explicitly uses 'Read,' which implies a non-destructive operation, and 'optionally filtering' conveys that unfiltered calls may return all messages. However, it does not mention permissions, response format, pagination, or any side effects, leaving room for improvement. The read nature is self-evident but lacks rich context beyond that.

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 sentence, front-loaded with the core action 'Read shared messages,' and every word is informative. There is no redundant or filler content, achieving maximum conciseness.

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 low-complexity read tool with two optional parameters and no output schema, the description sufficiently covers the main purpose and filter behavior. It implies that unfiltered calls return all messages, and the read-only nature is clear. It lacks explicit notes on return structure or edge cases, but for this simplicity, it is nearly complete.

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%, so the description must compensate. It explicitly states that filtering by task or recipient is optional, directly mapping to the task_id and recipient parameters. This adds meaningful semantics about their purpose and optionality, which the bare schema does not convey. It does not explain enum values or formats, but the schema covers those details.

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 'Read shared messages, optionally filtering for a task or recipient' clearly states the action (read), resource (shared messages), and optional filtering capability. It distinguishes itself from sibling tools like post_message (write) and task-management tools by focusing on reading messages.

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 indicates the tool is for reading shared messages, implying use when retrieval is needed, and the optional filtering context is presented. It does not explicitly mention alternatives or exclusions, but the read intent is unambiguous given the sibling tools, so it earns a 4 rather than a 5.

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