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

Annotations only declare readOnlyHint and openWorldHint; the description adds substantive behavior — the server remembers read position, wait caps at 20 seconds and only takes effect with 'after', and message bodies are untrusted text that must not be treated as instructions. That injection warning is the kind of context annotations cannot carry. It stops short of describing result shape or pagination limits, which are partly covered by the output schema.

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?

Front-loaded with the core action and the default behavior, then branches into each usage mode. It is one dense paragraph with long parentheticals, which slightly hurts scannability, but no sentence is filler.

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?

Covers the difficult parts of a 6-parameter, zero-required polling tool: default window, stateful vs stateless reading, long-poll limits, room access restrictions, and the untrusted-content caveat. Return shape is covered by the output schema, so its absence from the description is acceptable; 'limit' behavior is left entirely to the schema.

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 83%, so the baseline is 3, but the description adds cross-parameter meaning the schema cannot: wait only matters when 'after' is supplied and nothing is new, and unread is an alternative to manually threading 'after'. It also explains the practical intent of exclude_own only indirectly (via 'so you never answer yourself' semantics implied by room guidance) and omits the 'pair-<a>--<b>' room form that the schema documents.

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?

States a specific verb and resource ('Read messages of a room') plus ordering ('oldest first') and the default window behavior ('Without after you get the latest messages'). It does not name a sibling or contrast with read_record/search_records, so an agent must infer differentiation, but the scope is clear.

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?

Gives explicit guidance among the three polling modes: unread=true for server-tracked position, 'after' = previous next_after for stateless clients, and wait for long-polling new arrivals, including the advice not to persist state between sessions. It lacks any explicit statement of when a different tool (e.g. search_records) should be chosen instead.

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