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

Annotations only declare the mutation profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), so the description carries the real burden and does: it discloses that a preview is rendered, that base_template_id copies HTML and letter type (overridable), and enumerates hard rendering constraints (no scripts, no vh/vw, no box-shadow/transforms, single page margins) that an agent cannot infer elsewhere. This is materially more than the annotations provide.

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?

Purpose and the mode-selection branches are front-loaded and the HTML constraints are bulleted rather than run together, which suits their density. It is long and partially restates material it also points to (spur://letter-design-guide, spur://merge-variables), so a small amount of duplication keeps it from a 5.

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 covers what an agent needs to construct a valid call — modes, layout rules, image URLs, merge fields. It is slightly vague about the outcome: whether the template is persisted on this call or only previewed, and whether an id or preview URL is returned, is implied rather than stated.

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%, yet the description still adds operational meaning: letter_type is explained in terms of where the address prints and how much page the design can use, with concrete rules per enum value (3.15in blank address zone vs 1.8in letterhead, ~400 words). base_template_id scope is clarified (yours, Spur default, or gallery id) and start_from_blank is described as an empty laid-out page.

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 ("Create a letter template") plus an extra behavior ("show a preview"), and the letter-specific vocabulary (address zone, letterhead, letter type) clearly separates it from spur_create_email_template and spur_create_postcard_template. An agent can distinguish it from its siblings without opening the 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?

Gives three explicit entry paths (start_from_blank, base_template_id, raw html) with the conditions selecting each, plus routing to spur_list_images / spur_upload_image / spur_save_image when the user supplies images. It stops short of naming when NOT to use this tool (e.g. spur_update_letter_template for existing templates), so it is strong but not fully exhaustive.

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