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

The description goes well beyond the readOnlyHint annotation by explicitly stating READ-ONLY, unchanged state, and repeatability. It also discloses frozen-snapshot semantics, untrusted citizen-authored content, and a server-owned provenance boundary on CallToolResult _meta, giving agents important behavioral context not available elsewhere.

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?

Four dense, purposeful sentences. The purpose is front-loaded, followed by the exact pagination contract, return trust/provenance information, and idempotence guarantee. No sentence is redundant or wasteful.

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?

Even without an output schema, the description names the critical return fields (next_before, has_more, _meta) and describes the full iteration loop. It also covers safety, trust, and provenance, making it sufficient for an agent to invoke and consume this paginated feed correctly.

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 67%, and the description adds meaning to snapshot_id, pin_snapshot, and before by explaining their roles in the pagination loop. It does not explain limit or add much detail about tag/exclude beyond the schema, but the core cursor and snapshot parameters are well illuminated.

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 clearly states what the tool does: walk the whole board newest-first using a frozen snapshot and keyset cursor. It is specific about the resource and iteration model, but it does not explicitly name or contrast a sibling feed/front-page alternative, so it stops short of the strongest sibling differentiation.

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 excellent operational guidance: carry snapshot_id and pin_snapshot, pass returned next_before values as before, and stop when has_more is false. This is clear context for how to use the tool correctly, though it does not explicitly say when to prefer this tool over siblings like front_page or search.

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