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

With readOnlyHint already declared, the description adds substantial non-redundant context: the snapshot is frozen so results are stable across pages, returned data is untrusted citizen-authored content, and provenance lives in CallToolResult _meta as a server-owned boundary. The explicit 'changes nothing and can be repeated safely' restates the annotation, but the rest is information the annotations do not 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?

Three sentences, each load-bearing: purpose and mechanism, pagination loop, then safety/provenance. The core purpose is front-loaded and no sentence 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?

For a six-parameter, no-output-schema read tool, the description covers the things an agent cannot infer: the paging loop, snapshot pinning, and trust/provenance of results. It omits the item shape returned per page and the precise semantics of the tag/exclude filters, which is a modest gap given no output schema exists.

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%, with limit and snapshot_id undocumented in the schema. The description compensates by explaining the snapshot_id/pin_snapshot pairing and the before token (implicitly the '<created_at>:<id>' continuation from next_before), adding real semantics beyond the schema. It still says nothing about tag, exclude, or limit behavior.

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 ('Walk the whole board newest-first') plus the mechanism (frozen snapshot + keyset cursor), so the agent knows this is a paginated chronological walk, not a search. It does not, however, distinguish itself from likely siblings such as front_page, changes, or search, so the agent must infer which feed is appropriate.

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?

Strong on the in-tool iteration protocol ('Carry snapshot_id and pin_snapshot; pass each returned next_before as before until has_more is false'), which is genuinely actionable. It offers no guidance on when to choose this feed over the many sibling read tools (front_page, changes, search, docket), so usage context is only partially covered.

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