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

Beyond readOnlyHint it adds meaningful context: the response includes untrusted citizen-authored data, provenance boundary lives in CallToolResult _meta, and the nulls log behavior with eval paths ('done'/'id:'). The closing READ-ONLY line largely restates the annotation, but 'can be repeated safely' adds idempotency context.

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?

Front-loaded with the core action, then layers mode logic and behavior. Dense with domain jargon (docket:log-the-null, _meta) but each clause carries information; the trailing READ-ONLY sentence is the one portion that partially duplicates the annotation.

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 usefully sketches what comes back (catch-up feed plus the nulls log with reasons, untrusted author data, provenance in _meta). For a 4-parameter, security-sensitive read tool this is close to complete, missing only precise token/cursor lifecycle details.

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?

With 0% schema coverage the description must carry all parameter meaning, and it does: 'since' as a millisecond timestamp, 'posts_since'/'comments_since' as tokens starting with 'init' that carry returned tokens, and 'nulls_since' taking 'done' or 'id:<row_id>'. This compensates well for the empty schema, though exact token formats remain vague.

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 ('Read the catch-up feed') plus a temporal scope ('after a millisecond timestamp'), which implicitly separates it from siblings like newest_feed, events, and history. It stops short of explicitly naming what it is not, so it lands just under full marks.

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 rich guidance on how to invoke modes (lossless mode with posts_since/comments_since + 'init', silencing the nulls log with 'done', paging with 'id:<row_id>'). However, it never states when to choose this tool versus alternatives like newest_feed or events, so the when-to-use dimension is only implied.

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