update

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

With no annotations provided, the description carries the full burden. It discloses that file updates create a new version automatically and explains the file linking mechanism. It mentions that only passed fields are changed, implying partial updates. It does not cover permissions, rate limits, or async behavior, but the disclosed behaviors are sufficient for basic usage.

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 front-loaded with the main purpose and then delves into file-specific details. It is well-structured with a general paragraph and a dedicated subsection for file linking. While somewhat lengthy, every sentence adds value, and the separation of concerns is clear.

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?

Given 21 parameters and no output schema, the description covers the core behaviors and key parameters. It addresses file linking comprehensively but does not explain return values or versioning for non-file resources. The complexity is high, and the description provides sufficient detail for most use cases, leaving minor gaps.

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?

The description adds meaningful context beyond the schema, such as explaining that `id` must be a UUID from list/search/get, clarifying `isPrivate` for workflows, and specifying file linking syntax. Schema coverage is 67%, and the description compensates for several undocumented parameters (e.g., path, title) implicitly. However, some parameters like `workspaceId` and `changeSummary` lack extra guidance.

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 starts by clearly stating 'Update an existing resource in place by ID' and lists specific resource types like 'file, agent, skill, workflow, or project'. This distinguishes it from siblings like 'create' (new resources) and 'delete' (remove). The verb 'update' is specific and the resource scope is well-defined.

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 clear guidance on partial updates ('Only the fields you pass are changed') and version history for files. It also details file linking syntax and backlinks. However, it does not explicitly state when not to use this tool (e.g., for deletion vs update), leaving some assumption to the agent.

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