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

Annotations already declare readOnly, idempotent, non-destructive, which covers the safety profile. The description adds real behavioral context beyond that: newest-first ordering, a hard cap of 20 results (schema default 10), and that each item carries a link plus a conditional Auto Apply link. It omits pagination behavior and whether results are a stable snapshot, so it adds value without being rich.

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?

Two dense sentences with the core action and ordering front-loaded, followed by filter groups and return shape. No filler, no restatement of the title.

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 9-parameter, zero-required search with no output schema, the description covers both the filtering model and the return payload (up to 20 jobs, link, conditional Auto Apply link). Pagination or how to retrieve beyond the first 20 results is the one notable gap.

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 89%, so the baseline is 3, and the description earns above it by clarifying that no_degree, no_experience and visa_sponsorship filter on what the advert states rather than verified employer attributes. It also groups the filters conceptually, which helps an agent compose a query; it does not explain the limit parameter beyond the cap already implied.

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 live jobs on Haystack"), plus ordering ("newest first"), the filterable dimensions, and the result cap. The singular read counterpart get_job is implicitly distinguished by the search semantics, so an agent can tell search from fetch without opening either 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?

The description makes the use case clear: find jobs matching title words, location, remote, and advert-declared criteria. It does not name siblings (get_job, employer_facts) or state when-not-to-use, so routing is inferred rather than prescribed.

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