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

Annotations already establish readOnlyHint=true, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds behavior beyond that: page ordering (newest page first, oldest-to-newest within a page) and the cursor lifecycle (meta.nextCursor, null on the oldest page), which an agent cannot infer from the 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?

Two sentences, no filler. Scope and ordering come first, then the pagination instruction, so the most decision-relevant information is front-loaded.

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?

There is no output schema, and the description compensates by disclosing the meta.nextCursor envelope and the in-page ordering, which is what an agent needs to page correctly. It does not describe message fields or whether internal notes are permission-gated, but for a straightforward read-list tool this is close to 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 100%, so the baseline is 3. The description nonetheless adds meaning beyond the schema: it explains that `before` is fed from the page's meta.nextCursor and that its null value signals the oldest page, clarifying the cursor's provenance and termination condition. It does not elaborate on `limit` beyond the schema.

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 ('List a conversation's messages, replies and internal notes') plus the ordering contract, so it is clearly distinguishable from get_conversation, reply_to_conversation and add_note. It stops short of naming a sibling or scoping itself against one, so it is clear but not fully differentiated.

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 second sentence gives real guidance on when to use the `before` parameter (to page to older messages), which is genuinely useful. However, there is no guidance on when to choose this tool over get_conversation, search or list_* siblings, so usage is only partially addressed.

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