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

Annotations only declare this is a non-read, non-destructive write; the description adds the meaningful behavioral facts: the call is idempotent-style find-or-create rather than an unconditional insert, it requires write scope, and the campaign path has a membership precondition. Return shape and whether an existing conversation is returned unchanged are not covered.

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?

A single front-loaded sentence: verb, default scope, overriding scope, then the precondition and auth note. No filler, and the parenthetical constraint sits right next to the parameter it qualifies.

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 two-parameter write tool with full schema coverage, no annotations detail, and no output schema, the description covers mode selection, prerequisites, and auth. It could say a bit more about what comes back (existing vs newly created conversation), but nothing critical to invoking it correctly is absent.

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 already 100%, so the baseline is 3; the description earns above that by explaining what campaign_id actually selects (a campaign-scoped thread rather than the hub conversation) and the constraint that the contact must be in that campaign. contact_id semantics are left to the schema.

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 description pairs a specific verb phrase ('find-or-create') with a specific resource ('a conversation for a contact') and distinguishes two operating modes (hub vs campaign-scoped thread). It does not name any sibling tool, but the find-or-create framing already separates it from pure readers like get_conversation and pure creators like create_conversation_message.

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 states the default behavior (hub conversation) and the exact condition that changes it (passing campaign_id), plus a prerequisite constraint that the contact must belong to that campaign. What is missing is an explicit steer on alternatives, e.g. when to use get_conversation instead of a find-or-create.

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