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

Annotations already declare the non-destructive, non-idempotent write profile, and the description adds real behavioral context: the tool returns a phone preview with segment count and checks, messages are billed per segment, and links from unverified numbers can be blocked (justifying fallback_body). None of this 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 first sentence front-loads the action and its return value, and the second ties the artifact to its consumers. The SMS guidance block is dense but every sentence is actionable (segment limits, opt-out wording, link blocking, merge fields); it is slightly longer than strictly needed for tool selection.

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 still describes what comes back (phone preview, segment count, checks). It covers the two required parameters implicitly, names the reference resource for merge variables, and explains the compliance and deliverability rules an agent must satisfy before calling.

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 baseline is 3; the description goes further by explaining why fallback_body exists (link-free version when a URL causes blocking) and by documenting merge-field syntax like {{owner_first_name}} backed by the spur://merge-variables resource. It does not clarify is_default's interplay with existing defaults, so it is not fully complete.

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?

Specific verb and resource ("Save a new SMS template") plus a disclosure of a side-effect output ("show its phone preview with segment count and checks"). It distinguishes itself cleanly from siblings like spur_update_sms_template and spur_create_email_template, which target different channels or mutation types.

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?

States the downstream purpose by naming the exact consumers (spur_create_workflow / spur_set_workflow_step_template), which tells an agent why it would create rather than fetch a template. However it never explicitly routes away from alternatives such as spur_update_sms_template for edits or spur_preview_message_template for dry-run checks, so there are no stated exclusions.

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