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

Annotations already cover safety (read-only, idempotent, non-destructive). The description adds the supported metrics and typical applications, but it doesn't disclose edge-case behavior (e.g., dimension mismatch, zero vectors) or return formats beyond what the output schema would cover.

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?

Two clean sentences: first identifies the core function, second gives use cases. No wasted words, proper front-loading.

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 pure computational tool with strong annotations and an output schema, the description covers the essentials: operation, metrics, and use cases. It is sufficiently complete without needing to detail return types or edge cases.

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% and each parameter has a meaningful description. The tool description repeats metric names from the enum but does not add new parameter-level semantics beyond 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 description explicitly states the action ('Compute similarity/distance'), the input type ('two float vectors'), and the specific metrics (cosine, dot product, Euclidean, Manhattan). It also lists use cases, distinguishing it from similar sibling tools like similarity_score or embedding_similarity.

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?

Provides explicit use cases ('vector DB relevance scoring, embedding evaluation, and nearest-neighbor testing'), giving clear context for when to use. However, it doesn't mention alternatives or exclusions relative to sibling tools, so it's not a full 5.

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