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

Annotations indicate mutation/destruction, and the description adds meaningful context: it notes authentication requirements, describes return values (web URL, UUID), and explains the open-before-edit sequencing. It does not delve into destructive specifics, but the annotation already flags that.

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 opens with a one-sentence summary then uses a clean bulleted list for each action. Every sentence adds needed information—parameters, return values, and preconditions—with no wasted words.

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 multi-action tool with no output schema, the description covers return values, parameter defaults, sequencing, and authentication. It lacks error-handling details and explicit alternatives, but is sufficient for an agent to invoke the tool correctly in most cases.

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?

Although the schema has high coverage, its 'params' property just points to the description. The description compensates by fully listing each action's parameters, optionality markers, and default behaviors, which goes beyond the top-level schema.

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 this is for file management operations that create or modify state, and enumerates three concrete actions (open_file, create_file, close_file) with their resources. It distinguishes from siblings like files_read, though it does not explicitly contrast with write_data.

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 useful usage context such as requiring authentication, the need to open a file before editing, and the default behavior when team_uuid is omitted. However, it does not explicitly state when to use this tool instead of files_read or write_data, leaving some ambiguity.

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