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

Annotations already declare readOnly/idempotent/non-destructive, so the description's real contribution is the field projection ('selected operational fields'; notes, permissions, attachments, payroll omitted) and the access prerequisite. It does not say what happens when no contact matches the phone, which is the main behavioral gap.

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?

Four short, front-loaded sentences with no filler; the lookup key leads. The 'Read-only' clause mildly restates readOnlyHint, a minor redundancy.

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 one-parameter lookup with no output schema, disclosing which fields come back and which are excluded is the right compensation. Only the no-match/multiple-match outcome is left unstated.

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 0%, so the description must carry parameter meaning; it adds only that an exact, already-known phone is expected (as opposed to a search). Format normalization or exactness expectations beyond the schema's pattern/length constraints are not addressed.

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 plus the lookup key: 'Read one contact using its known phone.' That key implicitly separates it from constructiononline_get_contact and constructiononline_get_contact_by_email, though no sibling is named explicitly.

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 phone' plus 'requires customer API access' establishes the precondition for selecting this tool over the ID- or email-based lookups. It gives clear context but no explicit when-not or fallback guidance.

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