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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds genuinely useful non-obvious traits: it is non-persistent and the returned sources must be treated as untrusted data. It still says nothing about return shape or size/limit behavior, but the added context is real.

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 sentences, with the core action front-loaded and the non-persistence caveat immediately after. 'For free' is an unearned clause that adds no operational value.

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 should hint at the return value; it only implies a set of 'returned sources' via the untrusted-data warning. For a 2-required-parameter tool with zero schema documentation, more detail on inputs and return shape is needed.

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 0% for both parameters, so the description carries the burden and fails to explain what 'source' is (raw HTML/CSS? template id?) or the meaning of the sizes array entries and the 1-20 item limit. It only restates the two field names in prose.

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 concrete verb and resources: adapt a template source to target image sizes. It is distinguishable from siblings like edit_template or render, though it doesn't name them. The trailing 'for free' is marketing noise rather than purpose information.

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 clause 'This does not save the adapted source' implies when this tool is appropriate versus a saving tool like save_template, but no alternative is named explicitly and no prerequisites are given. Usage must be inferred.

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