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

Annotations only cover readOnlyHint and openWorldHint; the description adds substantial behavior beyond that: no fabricated results, retracted papers excluded by default, preprints included but flagged as not peer reviewed, and results interleaved by each database's relevance ranking. That is exactly the extra context annotations cannot carry.

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?

Front-loaded with what the tool is and its core guarantee, then filters, then defaults and ranking. Six tight sentences with no filler, every one carrying distinct information.

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?

Covers sources, the anti-fabrication guarantee, filtering behavior, default exclusions, preprint labeling, and ranking strategy; an output schema exists so return-field detail is not needed. Nothing material for correct invocation is 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 coverage is 100%, so each parameter's meaning and constraints are already documented. The description recaps the filter set (year range, open access, study types, result count) and the retracted default, but adds no syntax or semantics the schema lacks, so the 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?

States a specific verb (search) plus the exact resources (PubMed and OpenAlex) and a distinctive guarantee (every result has a resolving DOI or PubMed ID, so nothing is fabricated). This clearly separates it from siblings like verify_references and check_retractions, which operate on already-supplied references.

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?

"Finds sources for a claim or a topic" gives an implied use context, but the description never states when to prefer this over siblings such as verify_references or check_retractions, nor any exclusions. Usage is inferable but not guided.

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