create_analysis_block

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

Annotations only provide readOnlyHint=false and destructiveHint=false, so the description carries the behavioral burden. It richly discloses that formulas are auto-generated, that renames rebuild the total, that rows are tracked, that default aggregates are SUM for number fields, that removing the source cascades removal, and that double-counting is a risk. This is far beyond the minimal annotation coverage.

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 core purpose and stays on-topic, but it is somewhat lengthy. Every sentence contributes (formula generation, defaults, cascade deletion, describe_block hint, double-counting warning), yet the multiple paragraphs could be tightened without losing critical information.

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?

There is no output schema, but the description explains how the result is addressed via BLOCKREF and how to inspect it via describe_block. It covers the behavioral essentials: generated formulas, tracking, defaults, and cascade removal. For a creation tool with four parameters, this is complete enough 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?

Input schema coverage is 100%, so the baseline is 3. The description adds meaningful semantics: it explains the default aggregation behavior (SUM on number fields) and how the `aggregates` parameter overrides it, and clarifies the `source` relationship. It doesn't add detail for `name` and `label` beyond the schema, but the added value pushes it to 4.

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 and resource: 'Add a block that analyses another one — a totals row'. It distinguishes this from generic block creation by mentioning it sits below the table and that its result is addressable via BLOCKREF, which clearly separates it from siblings like create_block and create_pivot.

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 gives clear context: use this to create a totals row, don't write formulas yourself, and read it back with describe_block. It also warns against summing it alongside its source. However, it never explicitly names alternatives (e.g., create_block, create_pivot) or states when NOT to use this tool, so it stops short of full exclusion guidance.

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