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 still adds real operational context: a specific failure mode (reference_analysis_pending) and the retry pattern with retryAfterSeconds. That pending-analysis behavior is exactly the kind of thing that prevents a wasted failure loop, though the description says nothing about return format, caching, or limits.

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 short, labeled lines: purpose, usage trigger, and a concrete example payload, plus a one-line error-handling note. Nothing is wasted and the purpose is front-loaded ahead of the conditional guidance.

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?

For a read-only two-parameter tool with no output schema, the description covers selection and one error path but leaves the return value entirely unstated — an agent cannot tell whether it receives an image, a tile reference, or textual metadata about the region. That gap is significant given there is no output schema to fall back on.

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 100%, so both parameters (assetId from upload_reference_image, regionId from get_reference_regions) are already fully documented with patterns and provenance. The embedded example reinforces their pairing but adds no format or constraint detail the schema does not already carry, so baseline 3 applies.

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?

"Show a close-up of one numbered area" gives a specific verb (show/retrieve) and resource (a single reference region), which distinguishes it from the list-style sibling get_reference_regions. It does not explicitly differentiate from get_reference_tile, the other per-item reference reader, so the boundary remains slightly fuzzy.

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 when: an area's label or role is unclear" gives a concrete trigger condition for selecting this tool, which is more than most siblings offer. It stops short of naming when NOT to use it or pointing at alternatives such as get_reference_tile or submit_region_semantics for disambiguation.

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