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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=true, so the safety profile is covered. The description adds that omitting sections returns the base record, but says nothing beyond the schema about cost/latency of requesting many evidence sections, caching via freshness, or source-version pinning. Useful, but not rich behavioral context for a complex deep-fetch tool.

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?

Three short sentences plus an example, front-loaded with the primary action. The alternative-tool pointers come before the example, which is the right order. The example snippet is slightly raw but earns its place by showing the two required fields.

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 tool with 8 parameters, nested objects, 15 entities, and 61 possible sections, the description correctly delegates section discovery to get_capabilities and delegates return shape to the output schema. It doesn't explain how section_parameters keys relate to requested sections, which is the main residual gap, but overall it is adequate for the complexity.

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 88%, so the schema already documents id, species, sections, freshness, and section_parameters well. The description adds a worked example ({"entity":"gene","id":"PCSK9","species":9606}) that grounds the required entity/id pairing, but it introduces no new meaning about section_parameters keying or the entity-conditional section enums. 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 specific verb and resource ("Fetch one record by ID") plus the optional evidence-section dimension, and illustrates it across entity types (gene, drug, article, trial, protein). It also names the sibling it is not (get_variant_evidence) and the discovery sibling (get_capabilities), so an agent can separate this from the other retrieval tools.

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?

"Variants: get_variant_evidence" and "List an entity's sections with get_capabilities(entity=...)" route the agent to the right alternatives and implicitly say when not to use this tool. What is missing is guidance on get_record vs search_records/search_literature, i.e. fetch-by-known-ID versus discovery.

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