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

Annotations already declare readOnly=true, idempotent=true, openWorld=true, and non-destructive, so safety is covered and the description's job is to add behavior. It does add real facts beyond annotations: results are deduplicated, source outcomes are retained, and continuation is via an opaque cursor. However, these are compressed into a cryptic clause with no clarification of provider coverage, result-set semantics, or what "source outcomes" means.

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?

Two dense sentences with the purpose front-loaded, followed by an inline example and a documentation pointer; there is no padding. The middle clause ("deduplicate evidence and retain source outcomes and opaque continuation") is over-compressed to the point of ambiguity, which costs it a point.

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?

An output schema exists so return-value description is not required, but for a 6-parameter tool with a nested 13-field filter set and 17% schema coverage, the definition leaves major calling decisions (freshness, ranking_mode, limit ceiling, most filters) undocumented. An agent could call it, but not confidently configure it.

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 only 17% across 6 parameters and a 13-field nested filter object, so the description carries a heavy compensation burden. It mentions "publication/topic/source filters" generically and gestures at "opaque continuation" for cursor, but says nothing about freshness, ranking_mode, limit bounds, sort, or most filter fields (gene, drug, disease, open_access, no_preprints).

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?

"Find papers with publication/topic/source filters" gives a specific verb (find) plus resource (papers) and names the filter axes, so it is clearly a literature retrieval tool rather than a trial or variant lookup. It stops short of explicitly differentiating itself from siblings like trial_search, search, or variant_evidence, so it is clear but not sibling-routed.

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?

There is no explicit when-to-use or when-not-to-use statement, and no alternative tool is named; the agent must infer that this is the papers route from the word "papers." The example query and the guide URI imply usage but do not state conditions or exclusions.

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