loom_blacklist_add

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

The description adds substantial behavior beyond the annotations: admin requirements for org/global scope, a sweep cap, cross-writer tombstoning, and the `swept_truncated`/`sweep_error` completion signals. However, the disclosed sweep behavior (tombstoning matching rows, including other writers' rows) conflicts with the declared destructiveHint=false, so an agent reading only annotations would be misled about the destructive path.

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 WHAT/WHEN/WHEN NOT/ARGS layout is front-loaded and scannable, with no filler sentences. One line ('Refused to a token bounded to one user: a pattern refuses every user's writes') is grammatically murky and costs the reader a re-read.

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 7-parameter mutation tool with no output schema and no annotation detail, the description covers the important ground: privilege requirements, sweep risk and caps, and the failure-mode fields the caller must check. Only the undocumented `namespace` and `created_by` parameters keep it from being complete.

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 0%, so the description carries the burden. It documents 5 of 7 params meaningfully — the scope enum with its privilege gates, pattern_type enum, reason, sweep, and pattern — but omits `namespace` and `created_by` entirely, leaving two parameters undocumented in both schema and description.

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 WHAT section states a specific effect: every later memory write in the pattern's scope whose value matches `pattern` is refused. That is a concrete verb-plus-resource behavior an agent can distinguish from sibling tools, and the WHEN NOT line explicitly separates it from loom_memory_delete.

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?

Explicit WHEN ('never remember X', 'don't store anything about Y'), explicit WHEN NOT with a named alternative (forgetting one saved fact is memory.delete), and a conditional rule for when to set `sweep=true`. It also tells the agent what to do on incomplete sweeps (report and do not re-add), which is actionable guidance, not just context.

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