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

Annotations already provide idempotentHint=true and destructiveHint=false. The description adds meaningful non-obvious behavior beyond those hints: missing tags are created automatically, duplicate tagging is a no-op, and connected CRMs are kept in sync. 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?

Three sentences, all informative: the action, identification method, auto-creation behavior, idempotency, and integration side-effect. Front-loaded and free of filler.

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?

Good for the common case, but it never explicitly states that exactly one of lead_id or phone_number is required, and it does not describe the outcome if neither is provided. Since only tag is marked required in the schema, this ambiguity is a real completeness gap despite the description saying 'Provide this or...'.

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 coverage is 100%; each parameter already has a descriptive comment. The description adds the high-level relationship between lead_id and phone_number (one-or-the-other identification) but does not add much 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 opens with a clear verb and object ('Tag a lead by tag name'), then explains how to identify the lead via lead_id or phone_number. It does not explicitly contrast with sibling tools like remove_tag or add_note, but the operation itself is unambiguous.

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 gives clear operational context (which parameters to use, that unknown tags are auto-created, that duplicate tagging is a no-op), but it does not explicitly distinguish when to use this tool versus alternatives. No mention of remove_tag or when not to use this action.

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