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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), yet the description adds genuinely non-obvious behavior: the call is side-effect-free for the user ('nothing is shown to the user yet'), it emits presigned media URLs intended for context loading, and it hands off a resultId to sightglass_show. That stateful handoff contract is the kind of detail annotations cannot express.

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?

Three tight sentences, front-loaded with what is fetched, then the user-visibility caveat, then the follow-up call. No filler and no restating of the name or annotations.

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?

No output schema exists, so the description carries the return-shape burden and does so by enumerating the fields returned plus the media-URL capability. Combined with the resultId-to-show workflow, an agent has everything needed to call and act on 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 coverage is 67%: projectId and workspaceId carry their own descriptions (Replo ids, plan selection, multi-workspace requirement) while adId is self-evident from the description's 'fetch one ad'. The description adds no syntax or format meaning beyond the schema, so the baseline 3 is right.

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 ('Fetch one ad in full') and enumerates the payload: copy, creative caption, duplication facts, landing page, and presigned media URLs. This clearly separates it from sightglass_find_ads (discovery) and sightglass_show (rendering), so an agent can route 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 explicit downstream guidance: 'Once you know the answer, call sightglass_show once with this call's resultId,' plus the clarifying note that show does not search again. It stops short of naming the upstream path (sightglass_find_ads to obtain an adId), so discovery-to-fetch sequencing is left to inference.

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