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

Beyond the readOnlyHint annotation, the description adds valuable behavioral context: results are 'verifiable' with confidence/similarity scores and entity freshness, and the two modes have distinct output characteristics. This informs the agent about what to expect without needing to invoke the tool.

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 and front-loaded: purpose first, then modes, then result characteristics, then use case. Every sentence contributes meaningful information without redundancy or fluff. Length is appropriate for the tool's complexity.

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?

Given the schema covers all parameters and an output schema exists, the description provides the missing conceptual layer: when to use which mode, what to expect in results, and how to think about the domain scoping. It is complete for making an informed tool selection.

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?

While schema coverage is 100%, the description enriches parameter meaning significantly: it clarifies the tag/query mutual exclusivity, explains the semantic search mechanism (pgvector embeddings), and frames outputs in terms of 'domain-scoped shortlist.' This adds depth beyond the schema field descriptions.

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 clearly states the tool's purpose: 'Discover content franchises within a domain.' It uses a specific verb (discover) and resource (content franchises), and immediately distinguishes the two modes (tag vs query), which separates it from sibling tools like content_taxonomy and content_similar.

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?

Explicitly provides 'When to use:' guidance and explains which mode fits which intent (precise taxonomy match vs free-text semantic search). This gives clear direction for selecting the tool and its parameters, going beyond a simple statement of functionality.

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