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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds genuinely useful behavior beyond that: oldest-first ordering, a fixed page size of 20, cursor semantics for 'before', and the concrete shape of each returned record. It does not mention rate limits or total-count behavior, but the added context is substantial.

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?

Two sentences, front-loaded with the core action and pagination rule, followed by the return fields. The field enumeration is dense but each item is informational; no filler sentences.

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?

No output schema exists, so the description rightly enumerates returned fields (content, message_type with enum values, private, sender, created_at units, attachments). For a read-only list tool with full annotation coverage this is close to complete; only total-result/count behavior is unaddressed.

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 'before' and 'conversation_id' are already documented in the schema; the description largely mirrors that. It does clarify that 'before' is a message id returning the preceding 20, adding slight meaning, but the schema carries the load. Baseline 3 is appropriate.

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 and resource ('List the messages of one conversation') and constrains scope to a single conversation, which separates it from list-all siblings like conversation_list. It stops short of naming any specific sibling to differentiate from get_conversation or create_a_new_message_in_a_conversation.

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?

Pagination behavior is spelled out ('latest 20, or with before ... the 20 that came before'), which implies how to page, but there is no explicit when-to-use vs when-not or any mention of the alternative tools (get_conversation, conversation_filter). Usage is inferable rather than stated.

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