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

Goes well past the destructiveHint annotation by disclosing the full lifecycle: dedup matching against existing contacts by name/email/phone/address/reference, batching into an import at midnight, and commit only when a user reviews and clicks Run. The 'nothing is created in real time and no duplicates are forced' note is exactly the kind of consequence an agent needs before submitting.

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?

Front-loads the verb, resource, and recommendation, then uses the rest for genuinely load-bearing behavior (batching, midnight, manual commit). The middle sentence is dense with several dash-separated clauses and the trailing API path is low-value padding, but nothing is truly wasted.

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 23-param, zero-required, deferred-commit tool with no output schema, the description covers the critical unknown: what happens after submission and when data actually lands. It omits any guidance on minimum identifying fields needed and what the call returns, but those are moderate gaps given the annotations carry the safety profile.

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?

With only 48% schema coverage across 23 params, the description compensates by naming the fields that drive dedup matching (name, email, phone, address, reference), which explains why those parameters matter rather than just what they accept. It still leaves many address/name-component params (city, postal, suffix, address1/2, etc.) without added semantics.

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 ('Submit a new or updated contact') plus the mechanism (Virtuous's import pipeline), and explicitly positions it as 'the recommended way to add contacts' versus the read/side-effect siblings like search_contacts or add_contact_tag. An agent can identify its role 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?

Gives clear context for when to reach for it (adding or updating contacts, the recommended path) and implicitly what not to expect (no real-time creation). It does not name an alternative tool or state exclusions, so it stops short of explicit routing.

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