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

The annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description adds genuinely useful context: it may fetch elevation data and cache analysis inputs and results, and it explicitly frames output as screening-level. The caching remark sits slightly at odds with readOnlyHint, but as an internal cache it does not rise to a contradiction, and no limits, latency, or failure modes are described.

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?

Four compact sentences, front-loaded with the action and followed by prerequisites and caveats; no filler. The phrasing is slightly clipped ('May fetch elevation data'), but nothing is redundant.

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 an output schema present, the description need not explain return values, and it instead spends its space on interpretation limits, which is the right call for a screening tool. The main gap is the unaddressed slope_threshold_percent, plus no mention of cost or timing for the elevation fetch.

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%, so the description carries the full burden. It only partially does so: it says korzy_id must be verified and that the point must lie on that parcel, which gives real meaning to three required params. The fourth parameter, slope_threshold_percent, is never mentioned, so the agent gets no guidance on what the threshold does or how the resulting classification is produced.

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 verb+resource ('Analyze terrain over the full parcel polygon') is specific and scoped, and the caveats make clear this is a screening-level terrain analysis. It never distinguishes itself from the nearby get_terrain_metadata or get_site_context siblings, so the agent must infer which one to call.

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 gives a real precondition ('Use a verified korzy_id and point on that parcel') and warns what the results are not suitable for (grading/design, usable acreage, developable campus). What is missing is any routing to alternatives: it never says when to prefer get_terrain_metadata or get_site_context, or when a parcel-level terrain run is unnecessary.

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