get_sampleFetch a single EBI BioSamples record by accession. Returns the sample name, dates, taxId, organism, and a flattened map of its characteristics (organism, tissue, sex, cell type, etc.). Keyless.
| Name | Required | Description | Default |
|---|---|---|---|
| accession | Yes | A BioSamples accession like "SAMEA4451650", "SAMD00004696", or "SAMN...". |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare read-only and idempotent. The description adds that the tool returns specific fields (name, dates, taxId, organism, characteristics) and notes it is 'keyless', which is useful context beyond annotations.
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 with no fluff. First sentence states purpose, second lists return fields. Perfectly concise and front-loaded.
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 simple fetch-by-accession tool with no output schema, the description covers the purpose, input format, and output fields. No missing context given the low 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?
The schema already fully describes the accession parameter with examples. The description's mention of accession format repeats the schema's description, adding no new semantic value. Baseline 3 due to 100% schema coverage.
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 clearly states the tool fetches a single EBI BioSamples record by accession, specifying the source, action, and identifier. It also lists return fields, distinguishing it from the sibling 'search_samples' tool.
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?
While not explicitly stating when to use vs alternatives, the purpose is clear: use this tool when you have a specific accession and need full record details. The sibling 'search_samples' implies a search function, so context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Many tools overlap heavily: ask_pipeworx, ask_pipeworx_beta, and ask_pipeworx_grounded are near-identical variants (beta currently identical), and the set includes five-plus prediction-market tools (polymarket_arbitrage, polymarket_edges, polymarket_edge_tracker, polymarket_fill_risk, polymarket_kalshi_spread, bet_research) with fuzzy boundaries. Long descriptions help, but an agent selecting among them would frequently struggle to pick the right one.
Names are uniformly lowercase snake_case, but the pattern is inconsistent: verb_first names (search_samples, validate_claim, resolve_entity) mix with noun-style names (entity_profile, pipeworx_trending, polymarket_arbitrage) and bare imperatives (remember, recall, forget, subscribe). It is readable, but there is no predictable verb_noun convention across the set.
33 tools is well over the coherent range, and the count is especially inflated because the server is named Biosamples yet only two tools (search_samples, get_sample) actually belong to that domain. The remaining 31 tools are an unrelated mix of Pipeworx research, prediction-market, memory, and subscription utilities, including redundant variants.
For the stated Biosamples purpose, only search and retrieve exist—no submission, update, or batch operations—so the domain surface is a read-only fragment. For the broader accidental scope of the other tools, the set is a grab bag with no coherent lifecycle, leaving significant gaps regardless of which domain is considered primary.