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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds genuinely non-obvious behavior: all three contrasts are returned by default, missing values are included rather than omitted, and results are not a functional measurement — an important interpretive caveat. It does not describe response shape, but an output schema exists to carry that.

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?

Dense and front-loaded — the key input constraint comes first, followed by output scope and caveats. The telegraphic sentence fragments ('Exact symbol or Ensembl ID.') are efficient but slightly clipped, and the 'Returns ... missing values, source tables, citations and limitations' list reads as a run-on.

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 two-parameter read tool with a full annotation set and an output schema, the description covers input format, default scoping, and the major interpretive limitation. The only meaningful omission is routing to the search sibling when an exact identifier is unavailable.

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 it does: it specifies that 'gene' requires an exact symbol or Ensembl ID and explains that omitting 'contrast' yields all three contrasts. The enum values themselves remain documented only by the schema.

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 states the lookup key format (exact symbol or Ensembl ID) and the payload (DESeq2 estimates across three contrasts), which is enough to distinguish it from the sibling search_transcriptomic_genes by the word 'exact'. It never uses an explicit verb like 'fetch' or 'read', relying on the title for that, and it does not name the search sibling directly.

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?

'No automatic alias substitution' implies the caller must resolve aliases elsewhere, and 'unless one is specified' clarifies the default contrast behavior. However, it never explicitly says to use search_transcriptomic_genes to resolve a non-exact name, nor does it exclude any use case outright.

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