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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds behavioral context by specifying the return format (JSON with query, competitors, your_company_visible, gap_summary) and mentions it performs an analysis of AI search results. It does not disclose rate limits or error behaviors, but the core operation is transparent. No contradiction with annotations.

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 well-structured with a purpose statement, usage bullets, Args, Returns, and Examples. The purpose is front-loaded, and every section adds unique value. It is concise enough (about 150 words) while covering essential aspects, making it easy for an agent to scan.

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 a single parameter (nested object), an output schema (which defines the return structure), annotations covering safety, and a description that includes examples and return format, the tool is fully specified. An agent can determine how to call it, what to expect, and when to use it. No critical missing information.

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% for the top-level 'params' parameter, yet the description only says 'params (BusinessInput): Business details.' It does not enumerate the required fields (company_name, service, city) or explain how to fill them. Although the inner schema has property descriptions, the description fails to guide the agent on constructing the input, which is essential given the low coverage metric. The description should have compensated by listing the required fields or pointing to the schema.

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 statement 'Identify which competitors ARE appearing in AI search results when buyers search for a business's primary service in their city' names a specific verb, resource (competitors in AI search), and scope (primary service and city). This clearly distinguishes it from siblings like avenity_check_visibility (which likely checks the business's own presence) and avenity_score_business (scoring). The examples reinforce the purpose without ambiguity.

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?

A dedicated 'Use this when' section lists three explicit conditions: when clients want to know who outcompetes them, when personalizing with competitor names, and when building context for reports or outreach. This provides clear when-to-use guidance relative to the other tools, though it doesn't explicitly say when not to use, the conditions are sufficient.

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