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

Annotations only say this is a non-read-only, non-destructive write; the description supplies the real behavioral payload: the contact is auto-created or linked 'IN ALMOST EVERY CASE', contact_linked false means the lead is saved but orphaned and no tool can attach it later, retrying produces duplicates even on success, and no new-lead alert fires. It also discloses that the message is stored as the team's internal note and is surfaced with authorship attached in get_lead, list_leads and get_contact — none of which is derivable from the annotations or schema.

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?

The critical scope constraint is front-loaded, but the orphaned-lead warning is restated three times ('contact_linked false means...', 'THERE IS NO TOOL THAT CAN ATTACH IT AFTERWARDS', 'create_contact alone does not rescue this lead') and the message-authorship point is also repeated. The emphasis-by-capitals plus repetition inflates length beyond what the content requires.

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 carries the burden of the return value and does so by explaining contact_linked false in concrete terms (lead saved, no timeline, invisible to contact search). Combined with the mandatory source behavior, duplicate-on-retry warning and note-authorship disclosure, an agent has everything needed to call this correctly and to report the outcome honestly.

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 100%, so the schema already documents all four fields and the message semantics. The description still adds a cross-field constraint not present in the schema — 'Needs at least one of name, email or phone' — while the schema declares zero required parameters, which is genuinely load-bearing information for an agent.

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 and immediately narrows scope: 'Record an enquiry that arrived off-platform: a walk-in, a referral, a card taken at an event.' It also names the forbidden use case (backfilling leads that 'really came from a call, a form or an ad'), which cleanly separates it from form/call/ad ingestion paths and from create_contact.

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?

Explicit when-to-use (off-platform enquiry), explicit when-not (backfill from a call, form or ad) with the reason (source drives attribution and reporting), and an explicit alternative workflow when the lead is orphaned: create_contact then log_activity. It even rules out a tempting wrong fix ('create_contact alone does not rescue this lead').

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