Lookup Controlled Vocabulary

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

With no annotations supplied, the description carries the full burden and delivers a genuinely non-obvious behavioral trait: results come from an in-memory cache pre-fetched at startup and refreshed every 24 hours, with no API call at query time. That tells the agent about latency and the maximum staleness bound. It stops short of describing the return shape or whether the values are plain strings versus records with IDs.

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 opening two sentences front-load purpose and caching behavior, then a clean one-line-per-table list follows. Length is justified by 45 distinct enum values that each need disambiguation. Minor redundancy in repeating every enum name, but the accompanying glosses mean each line earns its place.

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 single-parameter lookup with no output schema and no annotations, the main remaining question is what comes back — a flat list of strings, or objects carrying ontology/UniProt/CDISC IDs (hinted at for lkDisease, lkProteinName, lkLabTestName but never stated). That gap matters because the agent cannot know whether it can pass returned values directly into filters or must extract a field.

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% — the enum lists bare identifiers like lkHmdb and lkVirusStrain with no explanation. The description fully compensates by giving a one-line semantic gloss for every single enum value, including example members and the domain each table serves, which is exactly the information needed to choose the right table.

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 ('Get valid controlled vocabulary values for any ImmPort lookup table') and enumerates all 45 tables with what each contains, so the scope is unmistakable. It does not explicitly contrast itself with siblings like get_data_model or search_studies, so an agent must infer the boundary from the resource name alone.

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?

Usage is only implied: the agent can deduce this is the tool for validating or discovering filter values before calling search_studies or get_assay_results. There is no explicit 'use this when...' statement, no when-not guidance, and no stated prerequisite that vocabulary values are required inputs elsewhere. The inline notes ('response field only, not filterable' on lkLabTestPanelName/lkLabTestName) are the closest thing to usage guidance.

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