load_demo

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

Beyond the annotations (destructiveHint=true), the description reveals the exact destructive and side-effecting behaviors: 'Stops the local draft monitor, replaces the snapshot, and resets configuration when the league changes.' It also documents what the tool does not do ('This tool does not connect to ESPN') and what it returns ('status='imported', revision, config_revision, and config_reset'). This adds substantial transparency beyond what annotations already disclose.

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 front-loaded with the main purpose and then provides behavior, prerequisites, and return values in a compact five-sentence block. Every sentence adds useful context. Only minor improvements—like merging the prerequisite and behavior sentences—could trim it further, so it earns a 4.

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?

Together with the rich annotations, the description gives an agent what it needs: purpose, alternatives, prerequisites, concrete side effects, and return values. It also explicitly clarifies it's not an ESPN connection. A small gap remains around what happens if the data directory contains non-synthetic state or how the 'empty or existing synthetic state' is validated, but overall it's sufficiently complete for safe invocation.

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%, and the input schema already gives the full meaning of the 'mode' parameter ('season' for weekly tools, 'draft' for draft simulations). The description does not add additional parameter semantics beyond that; it only repeats the same concept implicitly. Baseline 3 is appropriate because the schema carries the semantic weight.

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 opens with a clear verb and object: 'Load a fictional scenario for local testing or demonstrations.' It also explicitly distinguishes its purpose from a sibling by saying 'Use import_league_snapshot for your own data.' This makes the tool's intent unmistakable and differentiates it from the surrounding tools.

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 tells the agent when to use this tool (local testing/demonstrations) and names the alternative for different data ('Use import_league_snapshot for your own data'). It also states an important prerequisite: 'Requires an empty data directory or existing synthetic state.' It lacks a comprehensive 'don't use when...' list, so it earns a 4 rather than a 5.

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