Get Posting Statistics

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so the safety profile is covered. The description adds behavior beyond that: the US-only result scope, the fact that metrics default to unique_postings (clarifying the schema's null default), and the required prerequisite on filters.when. Return shape is not described, but an output schema exists so that is not a gap here.

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?

Three short front-loaded clauses with no filler: purpose and scope first, then the default, then the hard requirement and discovery path. The telegraphic style is efficient but slightly cryptic ('Discover filters and metrics in metadata' leaves the target tool unnamed).

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 two-parameter statistics query with an output schema and full annotation coverage, the description supplies scope, the required field, the default metric, and a discovery path for open-ended filter fields. The main residual gap is that the open-ended native JPA filter fields are only referenced, not characterized, which is a reasonable trade-off for a discovery-oriented API.

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?

With 50% schema description coverage and a nested, additionalProperties:true filters object, the description adds real meaning by naming the one required sub-field (when) and by pointing to metadata as the source of valid filter and metric names. It does not explain the two forms of `when` (the 'active' string versus the start/end/type object) or the expected format of the metrics array, so it only partially compensates for the coverage 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?

The description states a specific verb and resource ('Get US posting totals') and pins the geographic scope to the US, which separates it from broader siblings such as get_posting_rankings or get_job_posting_details. It stops short of explicitly naming which sibling covers rankings or per-posting detail, so the differentiation is implied rather than declared.

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?

It gives two concrete usage constraints: 'filters.when is required' and 'Discover filters and metrics in metadata', which effectively routes the agent to a metadata sibling before calling. However, there is no explicit when-to-use versus get_posting_rankings or get_job_posting_details, and no statement of what this tool is not for, leaving the choice of tool to inference.

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