ContextStream MCP Server

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint=true, destructiveHint=false, idempotentHint=true, and openWorldHint=false. The description adds value by revealing the tool's multi-action nature (22 distinct operations) and categorizing them into groups (Plan actions, Suggested rules actions, Team actions). This provides useful context about the tool's behavioral scope beyond what annotations convey, though it doesn't address rate limits, authentication needs, or detailed operational constraints.

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 a dense, unstructured list of 22 actions with minimal grouping. It's not front-loaded with the most important information, and the wall-of-text format makes it difficult to parse. While it avoids unnecessary words, the lack of structure and prioritization reduces its effectiveness as a quick reference for an AI agent.

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 complex tool with 40 parameters, 22 actions, no output schema, and rich annotations, the description is inadequate. It doesn't explain return values, error conditions, or how different actions relate to each other. The annotations cover safety aspects, but the description fails to provide the operational context needed to understand this multifaceted tool's complete behavior and integration points.

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?

With 100% schema description coverage, the input schema already documents all 40 parameters thoroughly. The description adds minimal parameter semantics beyond the schema - it only mentions that certain parameters apply to specific actions (e.g., 'query for recall/search/lessons/decision_trace'). This meets the baseline expectation when schema coverage is complete, but doesn't provide significant additional value.

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 states 'Session management operations' and lists 22 specific actions, which provides a general purpose. However, it's vague about what 'session management' entails and doesn't clearly distinguish this tool from sibling tools like 'memory', 'context', or 'project' that might handle related functionality. The description is more of a feature list than a clear statement of purpose.

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 no guidance on when to use this tool versus alternatives. With sibling tools like 'memory', 'context', 'project', and 'search' available, there's no indication of which scenarios warrant using 'session' versus those other tools. The description simply lists actions without contextual usage information.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.