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

Annotations already cover readOnly, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description adds useful context: the 1 km radius, distance-sorted results, and that the return value is a site_id — details not present in the annotations.

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?

The English and Korean sentences convey identical content, so roughly half the text is redundant. The useful scope constraint (1 km, distance order, site_id) is present but not front-loaded in a single efficient sentence.

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 no output schema, the description only states that a site_id is returned; it does not indicate what else accompanies it (name, distance, project stage) or how results are ordered beyond 'distance.' Adequate but leaves gaps for an agent interpreting the response.

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%, so both query and danji_id are already documented with examples and source hints. The description only echoes the two modes and adds the distance-sort detail, which is baseline-appropriate but not compensating beyond the schema.

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 (find) and resource (redevelopment/reconstruction project sites) with two search modes (within 1 km of a complex, or by name). It does not, however, distinguish itself from the sibling get_redevelopment, leaving the agent unsure which tool to pick.

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?

The two modes are implied by 'near an apartment complex (within 1 km) or by name,' but there is no explicit when-to-use-this-vs-get_redevelopment guidance and no stated precondition (e.g., requiring a danji_id from search_apartments even though the schema notes it).

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