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

Annotations already declare a read-only, idempotent, closed-world lookup, and the description does not contradict them. Beyond that, it discloses the meaningful behavioral nuance that winterStoragePrice is 'yard-confirmed, or null when unconfirmed' — a null-semantics warning the schema and annotations do not convey, and one that prevents the agent from treating null as an error or as zero. It does not discuss any not-found behavior for a bad id, 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?

One sentence, front-loaded with the verb and resource, with the routing hint and return-field detail packed into parentheses rather than separate clauses. No sentence is redundant against the schema or annotations.

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 single-parameter lookup with an output schema present and read-only annotations, everything the agent needs is present: the id source, the resource identity, and the one field whose semantics are ambiguous (nullable winterStoragePrice). No further explanation of return shape is required because the output schema carries it.

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% with a worked example ('meta-great-bay-marine'), so the baseline is 3. The description adds genuine provenance for the single required id parameter — that it must originate from find_yards — which is meaning the schema does not express and which prevents guessed or fabricated ids.

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 ('Get one yard listing by id') and immediately identifies the sibling that produces valid ids ('from find_yards'), so the agent can separate this lookup from the search tool without opening either schema. It also names the returned fields (website, phone, source note, winterStoragePrice), which sharpens what 'a yard listing' actually contains.

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 parenthetical 'from find_yards' encodes the prerequisite: this tool is the second step after a yard search has yielded an id. It stops short of stating when-not to use it (e.g. that it is not a search or bulk-fetch endpoint), so it is clear context rather than a full use/exclude matrix.

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