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

With annotations covering the safety profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false), the description still adds real value: short-lived URLs with an UTC expiresAt, screenshots reflect the saved program at capture time, and installation on the customer's site is not verified. The note that 'a failed inline image alone does not establish that the URL expired' is an unusually useful failure-mode disclosure.

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?

Six sentences but each carries distinct information: purpose, return shape, capture semantics, non-verification caveat, failure-mode caveat, boundary exclusions, and targeting rule. It is front-loaded and free of filler, though slightly denser than needed for a one-parameter tool.

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?

Even though an output schema exists (so return values need not be explained), the description still characterizes the returned URLs and their expiry, plus capture semantics and failure modes. An agent has everything required to decide when to call it and how to interpret the result.

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% for the single campaignId parameter, so the baseline is 3. The description's 'Targets campaignId if supplied, otherwise GROWSURF_CAMPAIGN_ID' merely restates the schema default, though it is worth noting the schema marks campaignId required while both sources describe an omitted-parameter default.

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 gives a specific verb+resource ('Capture temporary GrowSurf preview screenshots') and states the precondition ('after a draft program is saved'). No sibling tool produces screenshots, and the scoping to the referrer Window and referred-friend experience makes the output concrete.

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?

It clearly states the triggering context ('after a draft program is saved') and draws explicit negative boundaries ('does not accept arbitrary URLs, HTML, JavaScript, or external screenshot targets'). It does not name an alternative sibling, but no sibling performs this function, so the routing gap is minor.

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