poll_messages

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

With no annotations, the description carries the behavioral burden. It explicitly discloses read-only behavior and lack of cursor advancement, which is important. It also mentions binding_token for identity. However, it does not cover error handling, pagination behavior beyond max_results, or any side effects, so the disclosure is partial.

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 plus a clarifying clause. It is front-loaded with the core purpose and distinguishes the tool without waste. Every sentence adds value.

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 an output schema exists and parameter schema coverage is full, the description is sufficient for an agent to understand the operation. It covers the key behavioral constraint (read-only) and points to the sibling for cursor advancement. It does not elaborate on error conditions or advanced use cases, but these are largely covered by the schema and a read-only operation, so it is mostly 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 description coverage is 100%, so the schema already documents all parameters thoroughly. The description adds minimal parameter-specific meaning; it only ties after_seq to the 'newer than a sequence number' concept without extra detail. This meets the baseline but does not exceed it.

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 verb ('Read'), resource ('messages'), and scope ('in this session newer than a sequence number'). It explicitly contrasts with ack_messages by noting it does not advance the cursor, distinguishing it from that sibling.

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?

It clearly indicates the read-only nature and points to ack_messages for advancing the cursor, giving an explicit alternative. However, it does not state broader usage scenarios (e.g., when to poll vs. subscribe), though the contrast with ack_messages is strong and provides clear context.

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