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

The annotations already indicate read-only, idempotent, and non-destructive behavior. The description adds that no contacts are changed or stored and that invalid records produce individual errors, which is useful. However, it does not explain error formats, rate limits, or other side effects beyond what annotations already imply.

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 concise and front-loaded, using two sentences to convey the core operation, input constraint, error behavior, and optional capability. There is no extraneous information.

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?

The description leaves out critical context: the exact input format, the output structure, how records are identified, and what 'canonical duplicate candidates' means. While an output schema is said to exist, it is not provided, and the empty input schema combined with vague parameter references makes the tool incomplete for an agent to invoke correctly.

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?

The input schema is empty, yet the description refers to 'records with unique IDs' and 'optionally identify canonical duplicate candidates,' implying parameters that are not defined. The agent is given no information about how to specify the records or enable the optional duplicate-candidate mode, making the tool effectively unusable from the description alone.

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 that the tool normalizes up to 100 records with unique IDs and can optionally identify canonical duplicate candidates. However, it does not explicitly mention phone numbers in the description, relying on the tool name, and it does not differentiate itself from the sibling tools beyond a general batch-normalization role.

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 does not provide explicit guidance on when to use this tool versus the sibling phone-related tools. It mentions optional duplicate identification but gives no criteria for choosing this batch operation over single-record tools like analyze_phone_number or format_international_phone_number.

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