search_projectsOSF (Open Science Framework, by the Center for Open Science): search public research projects ("nodes") by title. Returns id, title, description, category, creation date, and tags. Keyless public data; the API can be slow.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max results (default 15, max 50). | |
| query | Yes | Title search text, e.g. "climate change". |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint, covering safety and idempotency. The description adds useful context (keyless public data, API slow) but does not contradict annotations. The additional behavior is moderate, so a 3 is appropriate.
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 just two sentences: the first defines purpose and output, the second adds access and performance context. Every sentence is necessary and information-dense with no fluff.
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 search tool with two parameters and no output schema, the description covers everything essential: what it searches, how to use it (by title), what it returns (specific fields), and important context (public, slow). It is complete.
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 100% as both parameters have descriptions. The tool description adds that the search is by title and lists return fields, but does not add new meaning to the parameters beyond what the schema provides. Baseline 3 is correct.
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 searches public research projects by title, specifying the source (OSF), the data type (nodes), and the returned fields (id, title, description, category, creation date, tags). This is specific and distinguishes it from siblings like search_preprints or get_project.
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 mentions 'Keyless public data' indicating no authentication needed, and warns that the API can be slow. It implicitly distinguishes from tools like get_project (by ID) or search_preprints. However, it does not explicitly state when to use or when not to use this tool versus alternatives.
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.
Several tools have near-identical or heavily overlapping purposes: ask_pipeworx and ask_pipeworx_beta are currently identical, ask_pipeworx and validate_claim both answer factual questions, and discover_tools and suggest_questions both surface capabilities. The dense set of Polymarket and entity-research tools further blurs boundaries despite long descriptions.
Names are consistently snake_case, but they do not follow a single predictable verb_noun pattern: actionable names like ask_pipeworx, search_projects, and compare_entities mix with noun-style names like polymarket_edges, pipeworx_feedback, and recent_changes. The convention is readable but not uniform.
34 tools exceeds the reasonable scope for a coherent server, and many are near-duplicate variants or members of sprawling tool families (ask_pipeworx variants, multiple Polymarket scanners, several meta/discovery tools). The set would be stronger with consolidation around a smaller number of distinct capabilities.
If this server is meant to provide OSF access, the surface is severely incomplete: only search_projects, search_preprints, and get_project exist, with no create/update/delete, file handling, registration, or contributor access. If it is meant to be a broader Pipeworx assistant, the OSF tools are unrelated and the domain is so scattered that coverage is incoherent.