get_taxonResolve a marine species/genus/family name against OBIS to its taxon record (taxon ID, rank, accepted name, kingdom/phylum/family/genus, and total occurrence-record count). OBIS = global ocean biodiversity occurrence database; complements GBIF with a marine focus. Keyless.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Scientific name, e.g. "Orcinus orca" or "Delphinidae". |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and no destructiveness. The description adds beyond annotations by specifying the tool is 'keyless' and detailing the exact return fields, which is valuable context for the agent. No contradiction with 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?
The description is extremely concise: two sentences. The first sentence front-loads the core purpose and return values, and the second adds useful context (OBIS, marine focus, keyless). No wasted words.
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 tool with one parameter, no output schema, and rich annotations, the description covers all essential aspects: what it does, what it returns, the data source, and authentication status. It is fully complete for an agent to understand and use the tool correctly.
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 description for the single parameter 'name' is already clear (scientific name with examples). The description adds context by specifying 'marine' and giving an example, aligning with schema examples. Since schema coverage is 100%, baseline is 3, but description adds meaningful marine context, justifying a 4.
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 verb 'Resolve' and the resource 'marine species/genus/family name against OBIS', and lists the specific fields returned (taxon ID, rank, accepted name, kingdom/phylum/family/genus, total occurrence-record count). It distinguishes from sibling tools like 'resolve_entity' by specifying the marine focus and OBIS database.
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?
The description provides context that OBIS complements GBIF with a marine focus, and mentions 'keyless' implying no authentication is needed. However, it does not explicitly state when to use this tool over alternatives or when not to use it, lacking explicit usage constraints.
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.
Most tools have distinct purposes and the descriptions are unusually thorough, but ask_pipeworx and ask_pipeworx_beta are explicitly identical right now, and several discovery/prediction-market tools (polymarket_edges vs polymarket_arbitrage, discover_tools vs suggest_questions) occupy overlapping territory. An agent could reasonably route to the wrong variant despite the documentation.
The dominant convention is lowercase snake_case with a leading verb (ask_pipeworx, list_subscriptions, validate_claim, resolve_entity), which makes the set predictable. A few noun-first outliers like pipeworx_trending, recent_alerts, and polymarket_edge_tracker are minor deviations rather than a broken pattern.
34 tools is well above the coherence sweet spot for an MCP server, and much of that count is made up of meta-wrappers and convenience variants around the same Pipeworx router. The broad scope explains some of the count, but the surface still feels heavy for a single named server.
The Pipeworx side is very complete: lookups, grounded verification, research, entity profiles, comparisons, prediction-market fill checks, subscriptions, and memory all have lifecycle coverage. However, the server is named Obis and only find_occurrences, get_statistics, and get_taxon serve that domain, leaving obvious marine-biodiversity operations like occurrence detail, dataset listing, and download paths missing.