Add a column

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

Annotations only say destructive/non-idempotent; the description adds the real behavioural detail: an undo reverts the column and the config line together, a backup is taken first, the write is refused when expected_version is stale, and the confirm/dry_run handshake is spelled out. That is exactly the context an agent needs before a destructive write.

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 with the action and placement, then the confirmation workflow, then safety guarantees — a sensible order. Dense but each sentence carries information; the opening clause about header styling is slightly convoluted but still earns its place.

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?

An output schema exists so return values needn't be described, and the description covers the remaining burden for a destructive, non-idempotent mutation: preview flow, confirmation token, version conflict handling, backup, and undo. Nothing an agent needs to invoke it safely is missing.

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 coverage is 100%, so the baseline is 3, but the description adds value by explaining why `field` exists (it makes other tools use the column) and by explicitly tying `expected_version` to a refusal on concurrent change. It does not elaborate on `kind`, `options` interaction, or header language, so it sits above baseline but not at 5.

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 and resource (add a column), plus the exact placement and styling rule: inserted after the last column with the header styled like its neighbour's. It also flags the config-mapping side effect for `field`, which no sibling tool does, so the agent can tell it apart from edit_application or fix_tracker.

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?

Explains when to set `field` (so the tools start using the column, checked via describe_tracker's unavailable_tools) and when to omit it, and gives the ordering rationale that columns must be added at the end. It does not name a sibling alternative to use instead when the column already exists, which keeps it short of a 5.

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