Swarm Intelligence

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

Annotations already declare readOnlyHint=true and idempotentHint=true, establishing the safety profile. The description adds real behavioral context beyond those: parallel multi-agent execution, an internal critique loop, and deduplication/false-positive filtering — traits an agent needs to know before invoking a heavy analysis. Nothing contradicts the annotations. It does not mention runtime cost or output shape, but the added behavioral color earns a 4.

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?

A single dense sentence that front-loads the core action (multi-agent parallel scan) before the qualifiers, and packs the covered domains and processing traits compactly. Slightly heavy with the colon-list plus trailing clause, but no wasted words and the most important information leads.

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?

Adequate for a moderate-complexity read-only tool: domains, parallelism, and output processing are covered. However, with no output schema present, the description should hint at the return format or the relationship to the other comprehensive siblings (verify_all, full_diagnose, audit_360, critique_report), and it does neither. For a heavyweight multi-agent scan, that is a meaningful omission.

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 100%: the single required `path` parameter is fully documented as the absolute path to the repository root. The description adds no parameter syntax or format detail, but none is needed for a single well-documented path argument. Baseline 3 applies since the schema carries the full semantic load.

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 composite action — a multi-agent parallel scan covering security, quality, memory, testing, and gaps, with dedup and false-positive filtering. Clear on what it does and the domains it spans. However, it does not differentiate from the sibling comprehensive tools (verify_all, full_diagnose, audit_360), which appear to serve an overlapping combine-everything role.

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?

There is no when-to-use or when-not-to-use guidance. With a long list of targeted siblings (security_scan, memory_scan, code_quality, test_coverage, gap_analysis) plus other aggregate tools (verify_all, full_diagnose, audit_360), an agent has no basis for choosing swarm_intel over a targeted scan or over a competing all-in-one. The implicit cue that this is the one-stop exhaustive scan is not stated explicitly.

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