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

Annotations already declare readOnlyHint=true, openWorldHint=true and destructiveHint=false, so the safety profile is covered. The description adds genuine context beyond that: it discloses provenance semantics (the connector returns only what the authority published, no computation) and the precedence rule that an authoritative registry outranks local data — useful for reasoning about result trustworthiness.

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 sentences, front-loaded with the core action and the authority examples. The second sentence is slightly editorial ('the rule that an authoritative registry outranks anything kept locally') but it earns its place by conveying the data-provenance boundary.

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 explained, and the authority enum enumerates all ~60 sources. For a read-only gateway the description covers the conceptual model adequately, though it says nothing about the project-record (_subject/_files) plumbing or rate-limit behavior across external authorities.

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 100%, so authority, query, limit and the nested _subject/_files parameters are all documented in the schema, including the command form example (`ensembl_lookup:BRCA2`). The description adds no parameter-level detail beyond that, 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 concrete verb and resource ('ask one of the ~60 authoritative databases a question and hand its rows downstream') and names example authorities, so the agent knows this is a connector/gateway rather than a compute tool. It does not, however, distinguish itself from the many sibling lookup_* tools (lookup_gene, lookup_protein, lookup_variant, search_literature), which cover overlapping territory.

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?

'Nothing here computes science' functions as a when-not boundary, steering the agent away for any analysis task, and 'hand its rows downstream' implies the fetch-then-process pattern. But there is no explicit routing versus alternatives like lookup_gene, fetch_record, or search_literature, leaving the choice to inference.

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