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

Beyond the annotations, the description discloses several useful behaviors: it tracks last_checked (consistent with readOnlyHint=false, since the call has a side effect), caps results at 3 items, and returns {new:0} when nothing matches. That last detail is valuable for parsing an apparently empty response, and the non-interference with recommend_tools clarifies downstream effects.

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 short and front-loads the core purpose, but the sentence 'When nothing matches, returns {new:0} — a minimal response when nothing new matches' restates the same fact twice and wastes space that could have gone to sibling differentiation.

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 one-parameter, non-destructive tool with no output schema, the definition covers the return shape ({new:0}), the result cap, the state it mutates, and its relationship to recommend_tools. The only meaningful omission is which sibling to use for a broader unfiltered feed.

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 100% and the single 'since' parameter is fully documented in the schema with the same 'YYYY-MM-DD or catalog version; defaults to last_checked' wording. The description adds no format or edge-case detail beyond that, so baseline 3 applies.

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 names a specific resource and scope: tools added or updated since the user's last check, filtered by their saved tags. The clause 'Does not change recommend_tools' helps separate it from the recommendation siblings, though the near-neighbor whats_new is never named, so full sibling differentiation is missing.

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?

Usage context is implied by 'since this user's last check' and the note that 'since' is optional and defaults to last_checked. However, there is no explicit statement of when to choose this over whats_new or fetch, and no exclusions or prerequisites are given.

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