Leapfrog MCP

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

Given no annotations, description carries full burden and discloses critical behavior: 'Executes each step directly against the browser' signals real side-effects, and explains the parameter substitution mechanism. Could further clarify state mutation risks or replay fidelity limitations.

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?

Four sentences with zero waste: purpose first, execution model second, parameter usage third, error handling fourth. Every clause earns its place; technical details are appropriately front-loaded.

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?

Covers core mechanics (replay execution, parameterization, error handling) but omits safety warnings about browser state modification and lacks output description. For a 4-param complex execution tool with no annotations and no output schema, this is adequate but incomplete.

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 coverage (baseline 3), description adds valuable semantic context: explains placeholder substitution syntax {{}} for 'params' object, and clarifies behavioral meaning of 'skip' (continue past failures) beyond the enum labels in 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?

States specific action (replay) and target (recording in current session) clearly. Distinguishes from session_create/export siblings by specifying 'current session' and 'executes steps', though could explicitly contrast with manual execution tools like 'act'.

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 implicit usage guidance through parameter override syntax ({{placeholder}}) and error handling hints (onError='skip'), but lacks explicit 'when to use this vs manual execution or session_export' guidance. Sibling relationships are not articulated in description text.

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