edit_analysis_block

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

The description discloses behavioral traits well beyond the annotations: aggregates replaces the set outright, omitted fields stop being computed and their cells go blank, the ref name is preserved so dependent formulas keep working, and the operation is one undo. This is exactly the side-effect transparency needed for a mutation 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 dense but well organized: purpose statement up front, then usage rationale, a critical replacement warning, and a routing comment about pivot alternatives. Every sentence contributes either action semantics, a caution, or decision guidance.

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 mutating tool with no output schema and minimal annotations, the description covers the important operational context: how to preserve existing aggregates (describe_block first), what happens when fields are omitted, that the block is ref-stable, and when to route to pivot tools. An agent has enough to call it correctly.

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, the baseline is 3, and the description still adds real semantic value: label doubles as the result key, aggregates is a wholesale replacement rather than an append operation, and field refers to the source block. The enum functions are not individually explained, but the schema already enumerates them.

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 specific verb phrase, 'Change what an existing analysis block computes,' and names the three mutable aspects: fields, aggregate function, and row label. It also distinguishes itself from pivot tools and from rebuilding by emphasizing the existing block and ref-name preservation.

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?

It explicitly says 'Use this to arrive at an analysis in STEPS' and advises adjusting rather than rebuilding because the ref name survives and the change is one undo. It also tells the agent when not to use it: for grouped aggregation, use create_pivot/edit_pivot instead. The alternative names appear with a 'build__' prefix, but the routing intent is unambiguous.

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