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

Annotations already cover the safety profile (read-only, idempotent, closed-world, non-destructive), and the description adds substantial behavior on top: the 20-item bound, newest-first ordering, that missing dates stay undated, that a supporting_context match is lexical rather than verified subject relevance, and that results are public metadata plus optional Blossom summaries with canonical IDs/links.

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 scope and ordering constraint are front-loaded, then caveats, then the hand-off to show_research_feed, so the structure matches how an agent reads. It is dense but nearly every clause carries decision-relevant information; the 'undated' clause and the plural 'filters' wording are the only slightly loose spots.

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 three-parameter, zero-required read tool with annotations covering safety and an output schema covering return shape, the description supplies what structured fields cannot: the bound and ordering, filter source, known data gaps, a relevance caveat, and the recommended follow-up call. Nothing an agent needs in order to call it correctly appears to be missing.

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 0%, so the description must carry parameter meaning, and it only partly does: it implies the 1-20 cap on limit (also in the schema's maximum/default) and characterizes compound and topic filters as drawn from the paper catalogue, but it never explains the query matching behavior, the maxLength, or the enum values. It adds some meaning over the bare schema but leaves the main text parameter underspecified.

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 ('published Blossom papers'), a cap ('up to twenty'), and an ordering ('newest recorded publication date first'), and it explicitly contrasts itself with a broader exhaustive literature search, which separates it from the search_* siblings. It also names show_research_feed as the display-only sibling, so an agent can route without opening a schema.

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 selection context: use this for a bounded catalogue page rather than an exhaustive literature search, and call show_research_feed with the returned IDs and the same filters when a browsable feed is wanted. It also warns to inspect the source before synthesis. It stops short of explicitly naming search_papers as the exhaustive alternative, leaving that contrast to inference.

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