blocked_traffic_rca

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

readOnlyHint=true already establishes the safe-read profile, so the bar is lower. The description adds real value beyond that: it discloses the internal classification taxonomy (port scan, service probe/brute-force, generic) and that a recommended action is attached to every row, which an agent needs to interpret results. No auth, rate-limit, or pagination notes, so not a 5.

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?

Front-loaded with the [READ] marker and one-line purpose, then mechanics, then Args and Returns. Given the 0% schema coverage, the Args section is load-bearing rather than redundant. Slightly long overall, but no sentence is wasted.

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?

With no output schema, the description properly documents the return dict shape ({blocksEvaluated, distinctSources, topSources:[...], note}) and the per-row fields, which is exactly what the agent needs. The main residual gap is sibling-level guidance on when to prefer this over firewall_log, but otherwise it is complete for a 4-parameter read/analysis tool.

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 0% — the schema provides only bare titles — so the description must carry the full burden, and it does. Each of the four parameters is documented with meaning and defaults: 'top' (rows, noisiest first, default 20), 'limit' (live rows to pull, default 500), 'log_entries' (with its field shape and that it skips the live pull), and 'target' (from config, omit for default).

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 opens with a specific verb pair (rank, classify) and resource (noisiest blocked sources), and states the exact mechanics — filtering to blocked entries, aggregating by source, and classifying cause. This is distinguishable from siblings like firewall_log or top_talkers, which neither aggregate blocked-only entries nor attach a cause/action classification.

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?

It gives clear operational routing: pass 'log_entries' for pure analysis, or a target to pull live. That tells the agent which mode to invoke and why. It stops short of naming alternative tools (e.g., firewall_log, rule_hit_and_shadow_analysis) or stating when this tool should be preferred over them.

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