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

Annotations already declare readOnly, idempotent, closed-world and non-destructive, so the safety profile is covered. The description adds genuinely new behavioral context: the data is a reviewed snapshot, updates require a deployment, so results can lag the live database — an important staleness signal an agent would not get from the annotations alone.

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?

A single dense sentence with zero filler, front-loading the concrete artifacts and ending with the snapshot-vs-live distinction that matters most for interpretation. It reads as a noun-phrase list rather than a structured statement, which slightly weakens scannability but costs no words.

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 values need not be restated, and the description supplies the framing an agent needs: what categories of provenance are included, that the source is a frozen archive rather than the live database, and how refreshes happen. Nothing further is required for a zero-parameter read tool.

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 tool takes no parameters, so there is no argument semantics to explain; baseline is 4. The description correctly does not invent pseudo-parameters and instead spends its words on what the parameterless call yields.

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?

Names a specific resource and enumerates its contents (Zenodo DOI, checksums, analysis commit, field definitions, pooled sample design, licences), which clearly distinguishes it from siblings like get_transcriptomic_gene or get_transcriptomic_robustness. It stops short of a verb-led statement such as 'Returns the frozen provenance record', so the agent infers the action from the name plus the inventory.

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?

The clause 'Separate from the live publication database' implies a when-to-use rule (consult this for archival/attribution facts, not current publication data), but no alternative sibling is named and no explicit exclusion tells the agent to prefer get_citation or get_transcriptomic_* tools for other needs. Guidance is implied rather than stated.

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