update_calculated_field

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

Annotations only carry destructiveHint=true, and the description meaningfully extends that: it discloses that the analysis definition is mutated, that a backup is created automatically, and that dependent visuals reflect the new expression immediately. Missing only permission/auth requirements and whether the change is reversible beyond the backup.

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?

Front-loaded purpose sentence followed by a compact warning block; every sentence carries actionable information (mutation, backup, immediate visual impact). No filler, though it is slightly more verbose than strictly necessary.

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 mutation tool with an output schema and a single destructiveHint annotation, the description supplies the key side effects an agent needs (definition change, automatic backup, immediate visual propagation). Only permission requirements and return-value framing are left out, which the output schema largely covers.

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%, so all three parameters (name, analysis_id, new_expression) are already documented in the schema. The description adds only the note that new_expression uses the same syntax as add_calculated_field, which is a small but real addition; baseline 3 is appropriate.

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?

States a specific verb (update), a specific sub-resource (the expression of a field), and a scope qualifier ('existing calculated field') that implicitly separates it from add_calculated_field and delete_calculated_field. It stops short of naming those siblings explicitly, so the differentiation is inferable rather than stated.

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 implies usage by requiring an existing field and warning about definition mutation, but it never states when to pick this over add_calculated_field or delete_calculated_field, nor what prerequisites (e.g. owning the analysis) must hold. Adequate but clearly incomplete guidance.

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