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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so safety is covered. The description adds genuinely non-obvious behavior: results are both returned to the assistant and persisted to the file store, and the data comes from two distinct sources (unit photos vs. unit UDF photos). It does not disclose the effect of max_images or whether results are paged.

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?

Front-loaded with the core purpose and the data-source scope, then the routing rule. The RM-desktop path narration ('Covers the Home > Property > Unit > IMAGES path...') is flavorful but slightly over-elaborate for an agent-selection description.

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 7 params, 0% schema coverage, and no output schema, the description should explain the remaining controls. It handles nomenclature and destination well but omits the image cap/limit behavior and what as_images=false produces, leaving real gaps for a multi-param tool.

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 0% across 7 params, so the description must carry the burden. It explains the shortname/property_id and unit_name/unit_id alternatives with an example, but says nothing about as_images, include_udfs, or the default max_images=6 — a behaviorally significant cap left undocumented.

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 ('Photos filed on one unit') and enumerates the exact data sources covered — unit IMAGES plus unit UDFs. It also names the sibling it is not: download_unit_attachment for non-photo files.

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?

Explicitly gives the when-not condition ('For a non-photo file on a unit UDF ... use download_unit_attachment') and a concrete invocation example with real argument values. The only unaddressed sibling is get_vacant_unit_images, which is a minor omission.

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