Leapfrog MCP

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

No annotations provided, so description carries full burden. Fails to disclose return format, pagination behavior (despite 'limit' parameter existing), or whether this is read-only/safe. 'Recall' implies non-destructive, but explicit behavioral traits are missing.

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, zero waste. Front-loaded with verb 'Recall'. Every word earns its place - first sentence states purpose, second states specific use case.

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?

Given 2 simple parameters and no annotations/output schema, description adequately covers core function but gaps remain. Should describe what 'actions' entails (browser events? API calls?) and return format since no output schema exists.

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 50% (limit documented, sessionId not). Description mentions 'this session' which implicitly contextualizes sessionId, but provides no explicit parameter guidance. Baseline 3 appropriate since it adds minimal semantic value beyond incomplete 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?

Description uses specific verb 'Recall' with clear resource 'actions performed in this session'. Effectively distinguishes from action-performing siblings (act, execute, navigate) and export/replay variants by positioning this as a retrieval/history tool.

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?

Provides specific when-to-use scenario ('after context window compression to recover lost context'), which is highly actionable. Lacks explicit naming of alternatives (e.g., session_replay vs session_memory), but the context window scenario clearly signals retrieval intent over other session tools.

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