Remove a file link

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

With no annotations, the description carries the full burden and does disclose the highest-risk behavioral fact: the operation affects only the link, not disk contents, which is the functional equivalent of a non-destructive guarantee. It still omits idempotency/error behavior (what happens if ref_id is already unlinked) and any permission requirements, so it is helpful but not complete.

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 short sentences, zero filler, with the scope-of-effect reassurance front-loaded immediately after the action. Every sentence earns its place.

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 simple two-parameter, no-output-schema tool, the description covers action, triggering condition, and effect scope, which is enough to call it correctly. The only real gap is not steering the agent toward or away from the adjacent link_files/delete_context tools.

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%: ref_id is documented as coming from the `files` of get_context or get_task, and model is described as the caller's model id. The description adds no parameter syntax, format, or constraint detail beyond repeating the link-not-file point, so the baseline of 3 applies.

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?

States a specific verb and resource (remove/unlink a file link) and clarifies the crucial distinction from file deletion: 'Removes the link, not the file' / 'Nothing on disk is touched.' It does not name a sibling (e.g. link_files for adding, delete_context for context deletion), so it stops short of a 5.

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?

Gives a concrete condition for use: links whose file 'was deleted, renamed or attached by mistake.' That tells the agent when this tool is the right one rather than a file deletion tool, though it offers no explicit when-not guidance or named alternative.

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