update_workitem

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

Annotations already declare readOnlyHint=false, idempotentHint=true, and destructiveHint=true, so the safety profile is covered. The description adds the non-obvious constraint that description cannot travel inside fields, which is real value. What is missing is whether fields is a merge or a full replace, and what happens to fields not listed — critical for a tool the annotations flag as destructive and idempotent.

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?

Two sentences, front-loaded with the action, then the parameter rule. There is no filler or restatement of the tool name, though the description is thin enough that brevity is partly a symptom of under-specification rather than discipline.

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 need not be described. But for a destructive four-parameter mutation with zero schema description coverage, an agent still lacks merge-vs-replace semantics, permission requirements, and any hint about the description_format enum. Adequate to attempt a call, not adequate to call it safely.

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 schema supplies only types, defaults, and a pattern. The description partially compensates by explaining that fields maps field identifiers to new values and excludes description, and that description has its own parameter. workitem_id and description_format (MARKDOWN/RICHTEXT) are left entirely to inference, and no example field identifiers are given.

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 uses a specific verb and resource ('更新...工作项') and scopes it to the current project, so the agent knows exactly which entity is being mutated. It does not explicitly contrast itself with siblings like create_workitem or update_workitem_comment, but the resource is distinctive enough that confusion is unlikely.

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 second sentence gives a concrete rule for splitting input between the fields map and the description parameter, which is genuinely useful operational guidance. However, there is no statement of when to prefer this tool over siblings, no preconditions (permissions, workitem state), and no warning about the destructive nature of the call despite destructiveHint=true.

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