things_update_item

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

With annotations already marking this as destructive and idempotent, the description adds meaningful behavioral context: partial updates semantics ('Omitted fields stay unchanged'), the special null-clear behavior for deadlines, and the explicit limitation that deletion and arbitrary property editing are not supported. This is consistent with the annotations rather than contradicting them.

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?

Three concise sentences, front-loaded with the core purpose. Each sentence adds necessary information: what the tool does, how updates behave, and what it explicitly avoids. No wasted words or restatement of schema properties.

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 rich annotations and an output schema, the description covers the important behavioral nuances: revision tracking, requestId uniqueness, partial updates, null clearing, and the no-deletion boundary. The main gap is the incomplete statement of target kinds (area and tag are present in the schema but omitted from the description), plus no explicit mention of behavior on a stale revision, though this is not critical for basic 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?

Schema description coverage is 0%, so the description must compensate. It explains the conceptual roles of requestId and expectedReversion ('unique UUID requestId', 'latest revision'), clarifies the changes object semantics ('Omitted fields stay unchanged; deadline null clears it'), and sets safety boundaries around target. It does not enumerate field names or value formats, but the schema provides those details.

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 identifies the tool as an update operation ('Edit supported fields, or complete/cancel/reopen a to-do or project') and distinguishes it from deletion tools by stating 'No deletion or arbitrary property editing.' However, it under-specifies the supported target kinds: the schema allows todo, project, area, and tag, while the description names only to-do or project for status changes, leaving area/tag update support ambiguous.

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 operational guidance ('Use the latest revision and a unique UUID requestId', 'Omitted fields stay unchanged') and a boundary ('No deletion or arbitrary property editing'), but it does not explicitly name alternatives like things_trash_item or things_move_item for other operations. Usage timing is mostly implied by the purpose rather than stated as a clear when-to-use vs alternatives rule.

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