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

Annotations correctly set readOnlyHint=false, destructiveHint=false. The description adds critical behavioral context: the tool only modifies the draft, changes are invisible until published if a published_version exists, and it clarifies error conditions (403 for system templates or cross-account). The description could add that the tool does not validate the schema or HTML for correctness, but overall it provides strong transparency.

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 description is a single dense paragraph. It packs essential context efficiently but could be split into bullet points or shorter sentences for easier scanning. Every sentence provides value, but readability suffers slightly from the dense format.

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?

Given 8 parameters, no output schema, and the complexity of draft/publish semantics, the description covers the most critical aspects: what the tool does, its limitations (draft-only), authentication requirements, and error conditions. It could mention whether the tool returns the updated template or just success, but overall it's quite complete.

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 50% (4 of 8 parameters have descriptions). The description fills gaps by listing which fields can be edited (name, html, css, schema, tags, visibility) and noting the UUID/slug addressing. It clarifies that only passed fields are changed. However, it doesn't elaborate on the format of the 'tags' array or the 'schema' object structure beyond what the schema provides.

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?

The description clearly identifies the tool as editing a custom template's DRAFT fields (name, html, css, schema, tags, visibility) and distinguishes it from operations that affect published content. It explicitly contrasts with render_pdf and publish_template, making the unique purpose unmistakable.

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?

The description provides explicit guidance on when to use this tool versus alternatives: it notes that edits won't affect published renders unless publish_template is called, explains when a 403 is returned (system templates or other accounts), and clarifies that the tool requires a specific API key scope. This helps the agent avoid misuse.

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