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

With no annotations, the description carries the full burden, and it does a good job: it discloses that results are sorted by renewal by default, that 'best' means cheapest USD across registrars, that 'registrar' switches to that registrar's own currency, that answers carry facet counts, and that 'trap' filters for 2x renewal. It also implies a read-only operation without stating it explicitly. It does not mention pagination limits or rate limits, but the schema already documents limit/offset defaults, so the description adds meaningful behavioral context beyond the schema.

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 description is compact and information-dense, with no filler. It front-loads the core purpose, then adds the most decision-relevant behavioral details (sort default, price semantics, facet counts, trap filter). Every sentence earns its place, and the structure flows logically from what the tool is to how results behave.

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 search tool with 13 optional parameters and no output schema, the description covers the key behavioral nuances an agent needs: default sort, price interpretation, facet counts, and the trap filter. It does not describe the exact shape of the answer items or how facets are structured, but since there is no output schema, a bit more detail on return format could help. Still, the description is complete enough for an agent to select and invoke the tool correctly for most queries.

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%, so the baseline is 3. The description adds value by explaining the semantics of 'best' and 'registrar' (cheapest USD across registrars vs. that registrar's own price in its currency), which the schema does not convey. It also clarifies the default sort rationale and the 'trap' filter's meaning. It does not add detail for every parameter, but the schema already covers them well, so the description's targeted additions are sufficient.

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 description opens with a precise statement of what the tool does: it searches top-level domains from IANA's root, and enumerates the data fields (type, registry, RDAP server, registrar prices). It also distinguishes itself from the sibling get_tld by covering the full set of TLDs with search/filter/sort behavior, and from tld_changes by focusing on current registry data rather than changes. The verb 'search' plus the resource 'top-level domains' is specific and unambiguous.

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 description explains the default sort (renewal) and why, and explains the 'best' and 'registrar' price semantics, which helps an agent decide when to use this tool. It also documents the 'trap' filter. However, it does not explicitly say when to prefer search_tlds over get_tld or tld_changes, nor does it state exclusions like 'use get_tld for a single TLD's full details.' The context is clear but the alternatives are not named.

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