multi_llm_citation_check

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

With no annotations, the description carries the full load, and it does disclose real behavioral traits: LLM answers vary run to run, each question is sampled `samples` times (default env var, max 10), and cost scales with questions x samples x engines. It does not explain what max_concurrency does or note the read-only/network cost profile beyond the scaling note.

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 headline sentence is front-loaded, the bullet list maps cleanly to output metrics, and the sampling/cost note is a tight closing paragraph. Minor redundancy between 'top_competing_domains and per-question results' and the output schema, but nothing gratuitous.

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 six-parameter, multi-engine batch tool with an output schema present, the description covers the workflow (feed questions, sample counts, cost), the key metric semantics, and brand-alias guidance. The gaps are the undocumented `engines` and `max_concurrency` parameters, which keep it from being fully 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 coverage is 0%, so the description must compensate. It explains `samples` (default env var, max 10), `brand_aliases` (with an example), and implicitly `questions` and `target_domain`, but leaves `engines` and `max_concurrency` completely undocumented — two of six parameters with no meaning anywhere.

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 gives a concrete verb+resource: it measures how often each configured LLM cites or mentions a target domain, with named metrics (citation_rate, mention_rate) and named engines. It self-identifies as the 'headline GEO/AEO tool', which helps an agent prioritize it, but it never explicitly differentiates itself from citation-checking siblings like aio_citation_check or perplexity_citation_check.

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 clearly tells the agent what to feed it ('your top 20-50 buyer questions') and when to pass brand_aliases ('if your brand isn't obvious from the domain'). No explicit when-not-to-use or named alternative routing, so it stops short of a 5.

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