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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered. The description contributes one genuinely non-redundant behavioral fact: the returned content is untrusted and must not be treated as instructions, which is a real prompt-injection guardrail. It does not disclose ordering, pagination termination, or empty-result behavior.

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 short sentences with no filler, and the untrusted-content warning is placed prominently rather than buried. It is arguably over-compressed — a three-word purpose clause would cost nothing and remove the inference burden — but nothing in it is wasted.

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?

With no output schema, the description ideally would say what comes back (message ids, authors, order). It does not, but the cursor model plus a 100%-covered parameter schema and full annotation set leave little ambiguity about how to invoke it, so the gap is small rather than crippling.

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 all four parameters (limit, since, api_key, match_id) are already documented in the schema, making 3 the baseline. The description's 'after a cursor' adds only a slight gloss on the `since` parameter and nothing on limit bounds or the auth fallback.

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 phrase 'Messages in a match after a cursor' identifies the resource (match messages) and the retrieval mode (cursor-based paging), which distinguishes it from send_match_message in the sibling list. However, it omits the verb entirely, so the agent must infer that this is a read/list operation rather than, say, a count or a filter preview.

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?

There is no guidance on when to call this versus alternatives such as get_match_receipt, poll_inbox, or list_matches, and no stated preconditions for obtaining a valid match_id or cursor. The only usable hint is the implicit 'after a cursor' framing for incremental polling.

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