Set the context routing mode for the organization. Requires admin role. Options: 'keyword_llm' (balanced), 'keyword_only' (fastest), 'llm_only' (most accurate).
| Name | Required | Description | Default |
|---|---|---|---|
| mode | Yes | Routing mode: 'keyword_llm' (keyword + LLM fallback), 'keyword_only' (fastest), or 'llm_only' (most accurate) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the disclosure burden. It mentions an admin requirement and the effect of setting the mode, but does not disclose potential side effects (e.g., impact on ongoing sessions, persistence, or whether the change is reversible). Adequate but not rich in behavioral context.
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, front-loaded with action, then requirements and options. Zero waste, every sentence 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 simple one-parameter setter with no output schema, the description covers the purpose, requirement, and options. It could mention that the current mode can be checked via get_context_routing, but that is implied by the sibling list. Essentially complete for its 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?
Schema description coverage is 100%, so the param is fully documented in the schema. The description repeats the options with slightly different qualitative labels ('balanced' vs 'keyword + LLM fallback'), adding marginal value but not meaningfully improving beyond the schema.
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 uses a specific verb ('Set') and resource ('context routing mode for the organization'), clearly distinguishing it from the sibling tool get_context_routing. It also enumerates the possible modes with qualitative labels, making the purpose unambiguous.
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 explicitly requires an admin role and explains the trade-offs of each mode (balanced, fastest, most accurate), helping the agent choose. It does not explicitly mention alternatives or when to use get_context_routing, but the context is clear enough for a simple setter.
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 resource+action pairs (e.g., create_task vs update_task vs delete_task), but the large number of list/get/search tools creates some potential confusion, especially between get_context, search_entities, and find_documents. Descriptions are detailed and help, but the volume makes navigation less clear.
The majority of tools follow a consistent verb_noun pattern (create_, delete_, list_, update_, etc.), with clear prefixes like add/remove and link/unlink. Deviations like 'whoami', 'find_documents' vs 'search_entities', and 'setup_organization' prevent a perfect score.
62 tools is far beyond the typical MCP server scope and overwhelms agents with too many choices. Even if each tool is individually useful, the sheer count makes it difficult for an agent to efficiently select the right tool, increasing the likelihood of misselection.
The domain is well covered for projects, tasks, teams, sessions, and notifications, but there are notable gaps: no update_document, no get_task (only list/update/delete), no get_user, no reject_invite, and sprint management lacks update/delete operations. Core CRUD is present for many entities, but not all.
