geo_audit

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

No annotations are provided, so the description carries the full burden. It does disclose the analysis dimensions (intent gaps, market white spaces) and the generated artifacts (BLUF blocks, Schema.org markup). However, it does not state whether the tool is read-only or mutates anything, whether it makes external network calls, or what side effects a full audit (including competitor and live-signal scans) may have.

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 description is two sentences with no filler. The purpose is front-loaded in the first sentence and the analysis/generation scope in the second. It is efficient, though it crams several specialized terms (BLUF, RAG-first, intent gaps, market white spaces) together without any elaboration or examples.

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 complex tool with five parameters but no output schema and no annotations, the description covers the high-level analysis and generation scope. Still, it relies on unexplained industry jargon (BLUF, RAG-first, intent gaps, market white spaces) and does not indicate what a returned audit report looks like or how live_signals/competitors affect processing — gaps the missing output schema and annotations would otherwise relieve.

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 100%, so the schema already documents all five parameters, including defaults and semantics. The description adds overall context (what 'rewrite' generates: BLUF + Schema.org) and clarifies purpose, but it does not add per-parameter detail beyond the schema. Baseline 3 is appropriate since the schema carries the 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?

The description states specific verb ('Audit') and resource ('website visibility in generative search engines'), naming the exact engines (ChatGPT, Perplexity, Gemini, Claude). It also conveys the distinct output (RAG-first BLUF answer blocks + Schema.org markup), which clearly differentiates it from its siblings_social_generate and agentic_scan.

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?

The description implies its use case (auditing generative-search visibility and identifying intent gapswhite spaces) and names its scope precisely, allowing an agent to infer when it applies. However, it never explicitly states when NOT to use it or points to a sibling alternative (e.g., when generation is needed use geo_social_generate). No exclusions are given, so selection relies on inference.

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