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

Annotations already declare mutation (readOnlyHint=false), idempotency, and non-destructiveness, so the bar is lower; the description still adds the non-obvious fact that an active workflow only applies the new template from the next send (no retroactive resend). It does not state what the previous template assignment becomes or how a type mismatch is rejected, leaving a small gap.

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?

Three short sentences, zero padding: the operation first, the required lookup second, the active-workflow caveat last. The parenthetical type mapping is compact and front-loaded rather than buried.

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 3-param mutation with no output schema, the description covers the crucial setup step, the semantic constraint tying step types to template types, and the effect timing on active workflows. It omits failure modes (invalid step_id, template type mismatch) and return content, which are the only remaining 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 coverage is 100%, so baseline would be 3, but the description adds real meaning: it constrains which template_id is valid for a given step type (email template for send_email, SMS for send_sms, postcard/letter for send_direct_mail), which the schema does not express. workflow_id receives no additional semantics beyond the schema's UUID note.

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 ('Set which saved template a workflow's send step uses') and immediately enumerates the three step-type → template-type pairings. An agent can distinguish it from sibling template tools (create/update/preview) and from workflow tools without opening a schema.

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?

Provides the concrete prerequisite ('Get step_ids from spur_get_workflow' via the step_id lookup) and the conditional behavior for active workflows. It stops short of naming an explicit alternative or a when-not case (e.g., use spur_update_email_template to edit template content first).

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