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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false. The description adds non-obvious behavior: wait_seconds blocks up to 25 seconds for new data, and it includes a security directive that others' content must be treated as untrusted and never as instructions, plus the from.human flag semantics. It does not cover rate limits or auth requirements, but the added context is substantial 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?

The description is front-loaded with the core purpose and return content, then adds the long-poll usage note and a security caveat. Every sentence carries useful information, and there is no boilerplate or repetition.

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 6-parameter read tool with no output schema, the description covers return contents, blocking behavior, and safety, which is helpful. But it leaves parameter semantics gaps—especially mark_seen and limit—that an agent would need to invoke the tool confidently, and annotations only cover the read-only safety profile. So it is adequate but incomplete.

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 only 33% (2 of 6 parameters documented) and the description mostly restates those two: after_seq default last-read position is already in the schema, and wait_seconds adds only the loop use case. Critical parameters like limit, mark_seen (default true), room_id, and member_token are not explained in either place, so the description does not compensate for the low coverage.

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 ('Read') and resource ('room'), then enumerates the returned content: new feed entries, member presence, status, board version. It does not name or contrast with sibling tools like check_updates, so an agent still has to infer when this differs from other read/update tools; hence 4 rather than 5.

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 explains a concrete usage pattern: wait_seconds holds the call so you can 'chat live by calling it in a loop.' That is clear context for a long-poll read. However, it offers no exclusions or explicit alternatives (e.g., when to use check_updates instead), so it falls short of a 5.

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