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

With no annotations, the description carries the full burden of behavioral disclosure. It explains inner workings such as the `free.today`, `free.label`, `free.next`, and `free.rules` fields, notes that free rules depend on the 'current LA date' (time-zone relevant), and lists additional return data (hours, open-now, visit length, quietest time, prices, links). This goes well beyond the schema and gives a detailed picture of behavior.

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 somewhat lengthy but is well-structured: it opens with the core purpose, then highlights two key differentiators with examples, and ends with a list of additional data points. Every sentence adds value, though it could be tightened without losing meaning. The front-loading is effective.

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 tool with no output schema, the description does a good job of enumerating return fields and filtering semantics. It covers free admission details, exhibitions, hours, open-now status, visit duration, quietest time, prices, and links. Missing details like pagination or error handling are non-critical for a finder tool, and the explanation of free rules is particularly thorough.

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 50% (type, limit, free_today have descriptions; lat, lon, open_now do not). The description adds meaningful context by enumerating museum types (matching the enum) and elaborating on the free-today concept. However, it does not explain lat/lon or open_now, nor does it fully compensate for the missing schema descriptions on those parameters. It provides partial value but leaves gaps.

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 begins with a specific verb and resource: 'Find Los Angeles museums and galleries'. It then lists concrete categories (art, history, science, film, kids, cars, gardens, photography) and highlights unique capabilities (free admission rules, exhibition schedules) that clearly distinguish it from sibling tools like find_bars or get_best_ticket_prices.

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 strong context for when to use this tool: 'Answers the two questions ticketing APIs cannot' (free admission and current exhibitions). This implies a contrast with ticketing-related tools such as get_best_ticket_prices, though it does not explicitly name alternatives or state when NOT to use it. The guidance is clear but not fully explicit.

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