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

Behavioral transparency is largely carried by the annotations (readOnlyHint: false, destructiveHint: true), and the description's 'Creates' is consistent with those annotations. The word 'reusable' adds a small hint that the artifact persists beyond the call, but the description discloses no further context such as overwrite behavior, quotas, or the fact that the template will later appear in list_templates.

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?

Two short, front-loaded sentences with zero filler: the primary action first, then the control hint. Minor deduction because the reference to 'selector' is used without acknowledging that it is documented in the richer content-object description rather than as a top-level parameter; otherwise the prose is economical.

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 the large nested parameter object and 11 siblings — including create_templated_image, update_template, and list_templates — the description does not place this tool in the template lifecycle (create once, render later with create_templated_image, update with update_template). The output schema covers return values, but the missing workflow context and selection heuristics leave the description incomplete for a tool of this complexity.

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 description coverage is 100%, with thoroughly documented parameters that include ranges, defaults, and pairing rules (e.g., device_scale defaults, both viewport dimensions required, jumbo_max constraints). The tool description itself adds no parameter-level meaning, so the baseline of 3 for high schema coverage applies; the nested content description also carries solid guidance for selector and template usage.

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 states a specific verb and resource: 'Creates a reusable HTML/CSS image template,' which at a glance distinguishes this from the one-shot rendering tools in the sibling list like create_image and create_url_image. The selector sentence adds a rendering-scope hint, but it does not explicitly name a sibling to route away from, so it stops short of a full 5.

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?

'Use selector when you want exact control over which element is rendered' is a within-tool rendering tip, not a tool-selection guideline. The word 'reusable' implies this is for artifacts intended to be used again later versus one-shot image creation, but no explicit when-to-use vs alternatives guidance exists, such as 'use create_templated_image to render an existing template.'

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