search_amazon_jobs

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

With no annotations, the description carries the burden well: it discloses that upstream matching is unreliable and that post-filtering is applied, which is real behavioral context an agent cannot get from the schema. It also explains the Pay field's provenance (local-law dependent, e.g. Canada). It stops short of stating result caps, deduplication across multiple queries, or whether postings include apply URLs.

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 verb and facets, then the caveats, then the disambiguation rule — a sensible order with no filler. It is on the long side and the paired examples are somewhat redundant with the job_category schema description, but each sentence still carries decision-relevant information.

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 an 8-parameter, no-annotation, no-output-schema search tool, the description covers invocation strategy, result trustworthiness, and a distinguishing data feature. Remaining gaps are minor and mostly schema-documented (sort, limit) — only cross-query result handling and return shape are 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 100%, so the baseline is 3, and the description earns an increment by adding semantics the schema does not convey: that title and job_category target different fields and return disjoint sets, with worked examples of each failing case. The anyOf (at least one of title/location/job_category) is never stated in prose, which keeps it from a 5.

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 amazon.jobs") plus the three facet dimensions it accepts, which immediately separates it from the sibling job boards (search_indeed, search_linkedin_jobs, search_google_jobs). The added note that pay bands are surfaced as a Pay field tells the agent what makes this source distinct.

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?

Explicitly explains that Amazon's native search is fuzzy and that title/location are re-applied against each posting, which tells the agent how to trust results. It goes further and states the exact selection rule between title and job_category (disjoint sets, with concrete examples) and when to run the category instead: "To survey a field rather than a job name, run the category too."

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