Block client

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

The description itself is maximally transparent about runtime behavior (no API call, error returned, retained only for compatibility), which is exactly the kind of disclosure an agent needs. However, it directly conflicts with the annotation profile (destructiveHint=true, readOnlyHint=false), which advertises a mutating operation that the description says never happens; the schema's 'confirm: YES to apply' also implies a real write. The description is the trustworthy party here, but the mismatch leaves the agent with contradictory signals.

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 with the disqualifying fact ('Not supported') front-loaded, followed by the reason and the compatibility rationale. Nothing is wasted and nothing essential is buried.

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 deprecated stub with no output schema, the description covers what an agent needs: it does nothing, it errors, and it exists only for compatibility. Naming the exact error or the preferred sibling tool for blocking would close the remaining gap.

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 coverage is 67%: confirm and dry_run are documented in the schema, while clientId is undocumented in both places. The description adds no parameter-level detail, and it implicitly renders the confirm/dry_run semantics moot by declaring the tool a no-op — useful to know, but not a semantics contribution beyond the 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 states a specific and unambiguous outcome: the tool is unsupported, the UniFi Network API defines no block action, and calling it returns an error without sending anything. That is far more informative than a generic 'block a client' phrasing and lets an agent immediately distinguish it from functional siblings like unifi_net_unblock_client or unifi_net_client_action.

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?

'Not supported ... returns an error and sends nothing. Kept for compatibility.' clearly implies the agent should not call this tool and explains why it still exists. It stops just short of explicitly naming the alternative to use instead, which is the only missing piece.

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