Get seen / blocklisted accounts

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

Annotations only declare readOnlyHint and openWorldHint; the description adds substantial behavior beyond that: pagination, newest-first ordering, the timing/visibility rules for held-back and rejected accounts, and the timestamp semantics (dated when first entering the pool). This is exactly the extra context annotations cannot carry.

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?

Purpose and scope are front-loaded in the first sentence and the closing `source` gloss is compact. The middle sentence about rejected accounts and the refund decision is dense and slightly circuitous, but it carries genuine information rather than 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?

With readOnlyHint set, no output schema, and three optional params, the description covers the semantic and timing nuances an agent needs. It leaves the paging parameters and the returned account fields unstated, which is a modest gap for a list tool.

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 0%, so the description must compensate for three parameters. It fully explains `source` ('run' = auto-collected, 'imported' = you added), and 'paginated' gestures at limit/offset, but neither limit/offset bounds nor ordering semantics for paging are spelled out.

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 your cross-run dedup pool') and defines scope precisely, including what is deliberately excluded ('accounts a relevance check is holding back are not listed'). It does not name the sibling tools (add_seen_accounts, reset_seen_accounts) it is implicitly distinct from, so sibling routing is left to inference.

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 gives real operational context — accounts appear only after a relevance check finishes, rejected ones only after the refund decision is recorded, and a naive sync 'can miss them'. That is useful when-to-use guidance, but there is no explicit statement of when to prefer this over alternatives or what prerequisite state must hold.

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