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

Annotations already flag destructiveHint=true, idempotentHint=false and readOnlyHint=false, so the safety profile is carried structurally. The description adds the useful mode-exclusivity rule but never says existing buyer-facing names get overwritten, nor what happens on a stale expectedUpdatedAt. Adequate, not rich.

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, then when-to-use, then exclusion, then a worked example — no wasted sentences. The example is somewhat long relative to the rest but earns its place by showing the field combination.

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 7-parameter mutation with no output schema, it covers mode selection, mutual exclusion, sequencing rules and a concrete call. The remaining gap is the effect on previously assigned names and conflict behavior on expectedUpdatedAt, which an agent would want before a destructive write.

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 baseline is 3; the description exceeds it by explaining how parameters combine into two alternative modes ('use scheme, startAt and direction, or names, not both') and by wiring the example to concrete values. It still doesn't clarify floorId scoping in prose.

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 ('Rename sections for buyers') and explicitly separates the two operating modes: positional sequence vs per-section names. It also pre-empts the nearest sibling with 'Not for: rows'.

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?

Gives concrete trigger phrasing ('number the sections 101 up, left to right'), names the exclusion (rows), and states the mutual-exclusion rule between the two modes. An agent can pick the right mode and reject bad inputs without opening the schema.

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