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

Annotations already declare this is a non-idempotent mutation, so the bar is lower; the description still adds real value by disclosing merge semantics ('Pass only the fields to change; nested objects merge') and the write_campaign_text side effect of reading their website and composing campaign text. It doesn't say what the draft save returns or whether validation errors are surfaced, and the website fetch is a mild tension with openWorldHint=false.

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 verb, resource and merge semantics, then moves to the decision rules. It is dense with countable value per sentence, though the run of instructions (type selection, IRS matching, consent, campaign drafting, review) is unbroken and could be chunked more clearly.

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 6-parameter mutation with nested objects and no output schema, it covers the classification and consent logic well but omits prerequisites (an existing phone number / texting setup, verification state) and gives no hint of what a save returns or how failures appear. Adequate but with clear gaps.

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 description coverage is only 17%, so the description must compensate — and it does for the load-bearing fields: registration_type's three-value decision tree, consent_channels' 'never invent consent' rule, and the dependency that write_campaign_text needs message_types and consent_channels. Nested address/contact/business_info fields get little narrative treatment beyond 'Business details must match IRS records exactly.'

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?

Opens with a specific verb and resource: 'Create or update the user's carrier (A2P 10DLC) registration draft.' The word 'draft' implicitly separates it from the sibling spur_submit_texting_registration, but that sibling is never named, so differentiation is left to inference.

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 concrete decision rules: registration_type from two questions (EIN? volume?), and 'Only record consent methods the user actually uses.' It also instructs the workflow 'Show that text to the user to review.' It stops short of saying when to use this versus spur_submit_texting_registration or spur_get_texting_setup.

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