fm_analyze

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

No annotations are provided, so the description carries full burden. It comprehensively discloses behavior: it performs pandas aggregation, returns compact summary tables, details behavior by parameter combination (groupby+aggregate, etc.), and notes no FM round trip. This is highly transparent for a read-only analysis tool.

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 well-structured and front-loaded with a clear summary, followed by efficiency note, detailed parameter combination behaviors, and then bullet-pointed args. However, it is somewhat lengthy and could be more concise (e.g., 'No FM round trip' appears twice). Still, it earns its sentences.

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 the tool's complexity (8 parameters, detailed combinations), the description is very complete. It covers all parameter behaviors, supported aggregate functions, examples, and return type. An output schema exists (mentioned in context), so the description need not detail return values. It is sufficient for correct 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 0%, so the description must compensate. It does so excellently by documenting each parameter with format, examples, and constraints (e.g., 'groupby: Comma-separated field names', 'aggregate: Comma-separated function:field pairs', 'filter: Pandas query expression'). This adds significant meaning beyond the bare 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?

The description clearly states it analyzes a loaded dataset with groupby/aggregation, distinguishing itself from siblings like fm_query_records by emphasizing it returns compact summary tables (~200 tokens vs ~400K tokens) and mentions 'No FM round trip'. This is a specific verb-resource combination that differentiates it well.

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 explicitly states when to use this tool: for aggregation/summarization instead of raw records. It also notes it works on previously loaded datasets or auto-populated table cache from query_records. However, it does not explicitly list when not to use it or provide alternative tool names, though the contrast with fm_query_records implies it.

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