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 real value beyond that: the results come from a frozen dataset version (Zenodo v1.2.0) and matches are "bounded" rather than exhaustive. It does not say how the bound interacts with limit/offset or what happens to the offset ceiling, leaving paging behavior partly opaque.

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?

Two short sentences with zero filler. The match-mode and dataset constraint lead, and the sibling exclusions follow, so the agent gets the discriminating information first.

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 no explanation, and the description covers dataset provenance, match mode, and scope. The remaining gap is pagination semantics for limit and offset, which matters for a tool whose result set is explicitly bounded.

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 description coverage is 0%, so the description carries the burden for three undocumented parameters. It does clarify the most important one — query is a literal gene symbol or Ensembl ID, not free text — but says nothing about limit, offset, or their interaction with the "bounded matches" claim, even though the schema caps them at 50 and 50000.

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 and resource: "Literal symbol or Ensembl-ID discovery" over "primary RNA-seq results" from a pinned Zenodo v1.2.0 dataset. It also excludes two neighboring modes (publication search, semantic search), which separates it from search_publications and search. It stops short of naming get_transcriptomic_gene, the sibling that fetches a single gene record, so the boundary there is implicit.

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 "not publication search or semantic search" clause is an explicit exclusion that tells the agent when to route elsewhere, and "literal symbol or Ensembl-ID" tells it when this tool is correct. What is missing is the positive alternative for fetching one known gene by ID (get_transcriptomic_gene) and any note on what to do when a literal match fails.

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