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

Annotations already declare readOnlyHint, idempotentHint, and openWorldHint. The description goes beyond this by specifying the output shape (dbname, primary ID, display ID, description), explaining the default behavior when dbname is omitted, and describing how returned IDs chain to protein, literature, disease, and pathway resources. It does not cover error-case or rate-limit behavior, so the remaining edge-case transparency keeps it from a 5.

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?

The description is front-loaded with the core purpose, followed by output format, filter behavior, chaining semantics, and prerequisite. The sentences are purposeful and efficient, though the 'Common dbname values' list partially duplicates the input schema and could be trimmed.

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?

Given the output schema, rich annotations, and schema descriptions, this tool definition is nearly complete. It covers the prerequisite (stable Ensembl ID), the default behavior (all xrefs), filtering semantics, and usage context. The main missing piece is a more explicit relationship to sibling tools, but that is not critical for basic invocation.

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 the input schema already explains both parameters thoroughly, including Ensembl ID types and common dbname examples. The description largely repeats the same enumerated dbname values and 'Ensembl stable ID' prerequisite rather than adding significant new meaning beyond 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 opens with a specific verb and resource: 'Retrieve cross-database references for a gene or feature' and lists concrete databases (HGNC, UniProt, EntrezGene, OMIM, RefSeq, Reactome). This clearly distinguishes it from sibling tools that handle homology, sequence retrieval, variant prediction, or region queries.

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?

It provides clear context: the tool requires an Ensembl stable ID and instructs the agent to 'use ensembl_lookup_gene first.' It also explains the optional dbname filter. However, it does not explicitly state when not to use this tool compared with sibling tools, e.g., when to choose ensembl_get_sequence or ensembl_get_homology instead.

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