search_papers

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

With no annotations, the description carries the burden and does disclose real behavioral traits: defaults require no credentials, max_results is per-source (not a total), and year_from is only honored 'where supported' — a meaningful warning about uneven backend capability. It stops short of saying what happens when an individual source fails or whether results are merged/deduplicated.

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 statement is front-loaded and the credential note follows immediately; the Args block is compact. Mild redundancy in restating parameter names, but each line adds at least one fact not in the schema.

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?

The output schema covers return values, and the description covers defaults, credentials, and per-source limits. For a multi-backend aggregator, however, it is silent on partial-failure behavior and result merging across sources, which an agent would reasonably want before calling it with several backends at once.

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 0%, so the description must compensate and largely does: it names all four parameters and adds semantics the schema lacks — sources must come from list_sources() and can be omitted, max_results is per source, and year_from is best-effort. The 'where supported' caveat is genuinely useful; only the format of sources entries is left implicit.

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 first sentence gives a specific verb and resource plus scope ('across one or many sources at once'), which is unambiguous. It does not, however, distinguish itself from siblings such as get_paper or run_research_pipeline, so the agent must infer the boundary on its own.

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 is implied rather than stated: 'Default sources are the ones that need no credentials' and 'Backend names from list_sources()' tell the agent how to activate non-default sources, but there is no explicit when-to-use versus get_paper/run_research_pipeline guidance and no when-not statement.

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