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

Goes well beyond the annotations: probe order (email first, then phone), merge semantics (only sent fields are written, omitted fields retain stored values, so a partial payload cannot wipe a curated field), and the constraint that status changes still pass through the transition machine and cannot jump to vip. That is precisely the kind of non-obvious, consequence-level detail annotations cannot express. Minor tension: annotations declare idempotentHint=false, yet the identity-keyed merge means a repeated identical payload would resolve to the same record rather than duplicate — not a flat contradiction, but worth noting.

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-loaded with the identity/matching rule and the merge safety guarantee, and every sentence carries operational content. The phrase 'the sync door the future desktop harness and ingest lanes write through' is mostly atmosphere, though it does hint at intended callers.

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?

Merge/patch semantics, probe order, and status-transition limits are all covered well, but two things an agent needs are missing: what happens if neither email nor phone is supplied (no required parameters are declared, so this is a real ambiguity), and what the call returns since there is no output schema to reveal whether a create or a merge occurred.

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 31% schema description coverage across 13 parameters, the description should compensate more than it does. It clarifies how email and phone drive matching and that note/notes and interaction/first_interaction accept the same composite children as contact_create, but says nothing about source, last_contact_at, tags, status enum meaning, or what happens when both identity fields are absent (required list is empty).

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 first clause names a specific verb and resource plus the identity rule: 'Create-or-merge a contact keyed on email-then-phone identity.' That framing immediately distinguishes it from contact_create (always creates) and contact_update (targets an existing record), so an agent can choose among the three without opening a 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?

It positions the tool for sync/ingest lanes writing partial payloads and explains that a miss creates while a hit merges, which is exactly the when-to-use condition. It never explicitly says when NOT to use it (e.g., a human editing a known contact should use contact_update instead of relying on probe order), 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.