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

Annotations already declare readOnlyHint/idempotentHint/destructiveHint=false, but the description adds real context beyond them: the shape of the return (selected operational fields only), the explicitly omitted data (notes, permissions, attachments, payroll), and the customer API access requirement. That goes meaningfully beyond the annotation profile.

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 short, front-loaded sentences: action and key first, return scope second, safety/prerequisite last. No filler and nothing redundant.

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 no output schema, the description compensates by naming what is returned and, importantly, what is omitted, so an agent knows not to expect notes or permission data. What remains thin is failure behavior (what happens if no contact matches the email).

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?

Only one parameter, and the schema's email format/pattern/maxLength already define its syntax fully. The description adds only the qualifier 'known', implying an exact-match lookup rather than a search, which is a small but genuine addition over 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?

States a specific verb and resource ('Read one contact') plus the lookup key ('known email'), which cleanly separates it from the sibling get_contact_by_phone and the id-based get_contact. An agent can pick it without opening the schema.

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?

'using its known email' establishes the precondition for choosing this tool over get_contact or get_contact_by_phone, and the read-only note confirms it is a safe lookup. It does not explicitly state when NOT to use it (e.g., the fallback if the email is unknown), so it stops short of full routing guidance.

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