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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive) and open-world scope, so the bar is lower. The description nonetheless adds real caveats: data is published and NOT a live clearance calculation, and users must verify access/operating details with the facility. It also notes the response carries source/freshness metadata. It stops short of describing pagination or result shape, which keeps it from a 5.

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 primary capability, followed by the sibling routing rule, then caveats and the units shorthand. Four sentences with no padding, though the caveat sentence and units line could be tightened slightly without losing meaning.

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 usefully signals that results include source/freshness metadata and that the data is authoritative-but-published rather than live. Combined with the units line, an agent has what it needs to call and interpret the tool; only pagination/limit behavior is unaddressed.

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% and the single parameter is a nested object whose fields (q, bbox, limit) have no descriptions, so the description must compensate. It does explain the bbox ordering convention (west,south,east,north) and the units/direction conventions, which are the genuinely non-obvious parts. It omits any mention of the limit parameter or its default of 20, leaving a gap.

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 ('search published sandbars') plus the two supported query modes (name, west,south,east,north bbox). It explicitly separates itself from list_spots for named recreational/scored spots, so an agent can distinguish it from that sibling and from the other find_* tools without opening any 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 an explicit when-to-use alternative ('For a named recreational/scored spot such as Lake Boca Sandbar, use list_spots first') and an explicit when-not ('avoid repeated searches for an already cataloged spot'). This is exactly the routing guidance an agent needs when ~100 siblings exist.

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