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

Annotations already declare non-destructive, idempotent, closed-world writes. The description adds real behavioral context beyond them: the plain-text version is regenerated unless hand-written or `text_body` is passed, workflows pick up the new version from their next step, and the 50,000-character ceiling. Minor tension with idempotentHint: replacements require `find` to occur exactly once, so replaying a call would fail rather than no-op.

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 editing behavior is front-loaded in the first three sentences, but roughly two-thirds of the text is an email HTML style guide (tables, preheaders, opt-out lines, merge fields) that overlaps heavily with the referenced spur://email-design-guide and spur://merge-variables resources. Useful content, but bloated for a tool definition and reusable across the create-template siblings.

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 an 8-parameter mutation with no output schema, this covers the essentials: what changes, how text regeneration works, downstream workflow effects, size limits and content constraints. One gap: the description calls it an email-template tool while the schema says `template_id` is an 'Email or SMS template id', leaving the SMS case unexplained given a separate spur_update_sms_template exists.

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, but the description genuinely adds meaning: it explains that `replacements` target 'html', 'subject' or 'text', that `find` is an exact match, and how `html` vs `text_body` interact. It leaves `name`, `description` and `is_default` entirely to the schema, which is acceptable given full coverage.

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 ('Edit one of the user's email templates') plus the visible outcome ('show the updated inbox preview'). The 'email' qualifier distinguishes it from the sibling update tools for letter, postcard and SMS templates without ambiguity.

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 explicit branch guidance: use `replacements` for tweaks, full `html` for a redesign, and pass `text_body` to override regeneration. It also routes the agent to spur_list_images / spur_upload_image / spur_save_image when the user wants their own assets, though it never says when to prefer spur_create_email_template over editing.

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