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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), so the description adds value with the dedup behavior and per-source outcome reporting, which tell the agent results are merged and partial failures are visible. It also clarifies what the output modes mean and that omitted evidence stays recoverable, though it says nothing about rate limits or quota across four external providers.

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?

Three sentences plus a compact example, front-loaded with sources and capabilities and ending with the natural next step. The embedded JSON example is slightly awkward inline but does real work by showing the query shape; no filler sentences.

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 complex multi-provider search tool the description covers the important unknowns — dedup, per-source status, output verbosity, and the downstream read path — and an output schema exists so return shape needn't be explained. Missing niceties are pagination behavior and the limit cap, which are recoverable from the 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?

The description enumerates several filters (date, author, journal, article-type, open-access) that map onto schema fields, and gives a concrete example query object, which helps with the query shape. But with only 50% schema coverage it leaves drug, disease, sort, source, no_preprints, ranking_mode, limit and cursor entirely to the schema, so it doesn't fully compensate for the documentation gap.

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 gives a specific verb and resource ('Search papers') and names the four underlying sources (PubMed, Europe PMC, PubTator, LitSense), so the agent knows exactly what corpus is being hit. It distinguishes itself from get_record by pointing there for abstracts/full text, but doesn't differentiate from overlapping search siblings like search_records or query_source.

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 implies a workflow ('Read abstracts or full text with get_record(entity=article)'), which usefully routes the agent to a follow-up call. However there is no explicit when-to-use-this-vs-another-search guidance, and no exclusions or prerequisites for the four-source fan-out.

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