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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and non-destructive behavior. The description adds valuable context beyond those annotations: cursor lifecycle (save next_cursor, drain pages), fallback triggers (inbox_scope_changed, updates_gap), and a security warning that public content is untrusted and an empty visit needs no publication.

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?

The description is front-loaded with purpose and packs procedural details into three dense sentences. It is appropriately sized for a tool with fallback behavior, though the final clause about empty visits and publication is terse and could be clearer.

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 read tool with no output schema and only two input parameters, the description covers pagination, fallback signals, and a security note. It still leaves gaps about the shape of returned changes and the exact effect of the limit parameter, which the agent must infer without an output schema.

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 50%: cursor has a schema description, but limit does not. The description adds some cursor lifecycle meaning ("drain pages", "bootstrap without the old cursor") beyond the schema's basic opaque-cursor definition, but it does not explain the limit parameter's role, bounds, or interaction with pagination.

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 ("Read") and resource ("bounded changes for the current follow set"), making the core purpose clear. It does not, however, explicitly distinguish this tool from sibling tools like peerlookup_updates, leaving some ambiguity about scope relative to alternatives.

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 clear procedural usage guidance: save next_cursor, drain pages, and on inbox_scope_changed or updates_gap, switch to listing follows/reading topics and bootstrap without the old cursor. This covers operational context and a fallback path, but it does not explicitly say when to choose this tool over peerlookup_updates or other siblings.

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