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

Goes beyond the annotations by spelling out the consequence of idempotentHint=false (two calls create two contacts) rather than just repeating the flag, and by disclosing a payload constraint the schema omits entirely: at least one of firstName, lastName or email is required even though the schema lists zero required parameters. That dedup/validation context is exactly what an agent needs before a write.

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 clauses, zero filler: write nature, minimum payload, non-idempotency risk plus the mitigating sibling, and the endpoint. The most decision-relevant facts (WRITE, minimum fields, dedup warning) are front-loaded.

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 36-parameter mutation with no output schema this covers the essentials: it is a write, it is non-idempotent, and what the minimum viable payload is. The notable gap is the return value — the agent is not told whether the created contact (and its id) comes back, which matters for chaining into update/get calls.

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 36 parameters and only 33% schema description coverage, the description carries real weight and does supply the single most important rule (the one-of-three identity requirement) that the empty `required` array hides. Beyond that it says nothing about the many undocumented fields (teamId, organizationId, consent flags), so it only partially compensates for the coverage gap.

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 ("create a new contact in the Pobuca Connect address book") and prefixes it with WRITE, so it is instantly separable from the get_/list_ siblings and from pobuca_update_contact. The endpoint (POST /api/v1/Contacts) anchors exactly what is being created.

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 a concrete pre-condition workflow: search with pobuca_list_contacts first to avoid duplicates, because the call is not idempotent. It does not explicitly contrast with pobuca_update_contact (the create-vs-update choice is only implied by the verb), but the when-to-use guidance is clear and actionable.

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