update_unit

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It reveals that a snapshot is taken before the write (enabling restore_unit), that versionReason is mandatory, and that ifUpdatedAt is used for optimistic concurrency to prevent clobbering. This is valuable context, but it omits details like partial update semantics, return values, and permission requirements.

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 compact and well-structured: a leading purpose statement, a behavior note (snapshot), and two imperative usage tips. Each sentence earns its place with no filler. Front-loaded with the primary action, it is easy to parse and understand at a glance.

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 tool with 30 parameters, no annotations, and no output schema, the description covers the most critical operational aspects (snapshot, versionReason, ifUpdatedAt) but omits other important context such as partial vs. full update behavior, what the response contains, and any prerequisites or permission concerns. It is adequate for safe invocation but not fully complete given the tool's complexity.

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 only 7% (only ifUpdatedAt and versionReason have descriptions). The description names a few fields informally (rent, tenant) that do not directly match the schema fields (rentEuros, tenantName, tenantEmail), which could confuse an agent. It does clarify the purpose of versionReason and ifUpdatedAt, but the remaining ~28 parameters are left to self-explanatory names without semantic explanation.

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 clearly states the tool writes Properties fields (squareMeters, rooms, rent, tenant, notes, …), making the action explicit. It also distinguishes itself from siblings like get_unit (read) and restore_unit (undo) by referencing the snapshot mechanism and concurrency handling.

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 provides concrete usage direction: always pass versionReason, and use ifUpdatedAt from get_unit.updatedAt to avoid clobbering. It also implies when to use this tool (writing properties) and when to use restore_unit (undoing a bad write), though it does not explicitly list exclusions or alternatives beyond restore_unit.

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