search_casesSearch NCI GDC cancer cases (patients/samples) by primary site and/or project. Returns case_id, submitter_id, primary site, disease type and project_id. Keyless, open-access metadata.
| Name | Required | Description | Default |
|---|---|---|---|
| size | No | Number of cases to return (default 20). | |
| project_id | No | Restrict to a GDC project, e.g. "TCGA-BRCA". | |
| primary_site | No | Primary anatomic site, e.g. "Kidney", "Breast", "Bronchus and lung". |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Input schema / examplesAdded value: +[
+ {
+ "primary_site": "Breast",
+ "project_id": "TCGA-BRCA"
+ },
+ {
+ "primary_site": "Kidney",
+ "size": 50
+ }
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and openWorldHint, so the safety profile is clear. The description adds value by listing the returned fields (case_id, submitter_id, primary site, etc.) and specifying it is 'Keyless, open-access metadata', which goes beyond annotations. No contradictions.
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), front-loading the core action and resource, then listing key return fields and access notes. No unnecessary 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?
The description covers the tool's purpose, filters, and return fields. However, it omits mention of the 'size' parameter for pagination, which is documented in the schema but not in the description. Given no output schema, the return field list is helpful, but a mention of pagination would improve completeness.
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 coverage is 100% with clear parameter descriptions. The description mentions primary_site and project_id as filters, but adds no additional meaning beyond what the schema already provides. Baseline 3 is appropriate.
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 it searches NCI GDC cancer cases (patients/samples) by primary site and/or project. It specifies the resource (cases) and the filtering criteria, distinguishing it from sibling tools like 'search_files' which target files.
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 indicates this tool is for searching metadata by primary site and/or project, but does not provide explicit guidance on when to use it versus alternatives (e.g., 'search_files'). The 'Keyless, open-access metadata' note hints at the access context but lacks explicit exclusions.
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, but ask_pipeworx and ask_pipeworx_grounded overlap in routing (differ only in answer mode), and the multiple Polymarket tools (bet_research, polymarket_arbitrage, polymarket_edges, polymarket_kalshi_spread) could cause confusion without careful reading of descriptions.
Naming mix of verb-first (ask_pipeworx, compare_entities) and noun-first (entity_profile, recent_changes) patterns. Most use snake_case consistently, but the pattern is not uniform—some tools are commands, others are descriptors. Notable deviations like 'pipeworx_feedback' and 'pmc' are missing here but the sample shows inconsistency.
30 tools is on the high side, but the server covers a broad domain (data lookup, betting, AI, genomics, memory). Some tools could be merged (e.g., ask_pipeworx and its grounded variant), and the betting subdomain feels over-instrumented. The count is borderline between appropriate and heavy.
The server provides a wide range of operations for its diverse domains, but gaps exist: the genomics tools only offer basic metadata search (no download/analysis), and the betting tools lack historical data or backtesting. It covers common patterns but with notable omissions for a cohesive experience.