delete-agent-files

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

With no annotations, the description does carry useful weight: it explicitly flags the operation as destructive, requires confirmation, and names the underlying SDK method and HTTP verb. But critical behavior is undisclosed — whether this unlinks files from the agent or permanently deletes them from storage, whether it is reversible, and how partial failures across multiple `file_ids` are handled.

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 short sentences with the destructive warning placed last, which is a reasonable emphasis position. The "Mirrors `syntx.agents.deleteFiles`" sentence is marginal value for an agent that cannot call the SDK, but it is one clause and does not bloat the definition.

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 two-parameter destructive tool with no annotations and no output schema, the definition covers identity, endpoint, and the confirmation requirement. It stops short on the two things an agent most needs before a destructive bulk call: the blast radius (unlink vs. permanent delete) and what the response reports back.

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 100%, so both parameters are already fully documented in the schema, including where to obtain `agent_id` and `file_ids`. The description only restates the payload shape `{file_ids: [...]}` and the path segment, adding no new meaning about ordering, limits, or atomicity.

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?

"Remove files from an AI agent" gives a specific verb and a scoped resource, and the endpoint path `DELETE /api/v1/agents/files/delete/{agent_id}` pins down exactly which operation this is. It is clearly not `delete-agent` or `delete-file`, but the description never explicitly contrasts with those siblings, so differentiation is inferred rather than stated.

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?

"Destructive — confirm before invoking" is a real usage directive, and the schema's references to `list-agents` and `list-agent-files` imply the prerequisite lookup workflow. However, there is no guidance on when to choose this over `delete-file` (deleting a file outright) or when to use `add-agent-files` to correct a mistake, so the when/when-not is only implied.

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