HirePulse Agent Gateway

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

Annotations already declare readOnlyHint=true and openWorldHint=true, but the description adds real value beyond them: it discloses the exact data sources probed and states that blocked, unreachable, nonexistent, and no_signals pages are not charged. Cost behavior is agent-relevant context that structured fields do not carry.

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 no filler, front-loaded on the detection scope and followed by the billing caveat. Slightly clause-heavy in the first sentence, but every clause conveys distinct 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 a single-parameter, read-only detection tool with no output schema, the description covers what is scanned, the scope constraints, and the cost exclusions. It could say more about the shape of the result, but the essential call-time information is present.

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 description coverage is 100% and the single 'domain' parameter is fully documented there (no scheme, path, or port). The description's 'Single domain' adds only a marginal reinforcement of what the schema already establishes, so the baseline 3 applies.

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 (Detect) and enumerates the exact resources examined: technologies, ad pixels, DNS signals from home page, HTTP headers, cookies, and up to two GTM containers. An agent immediately knows what it gets and the scope ('Single domain'), and the only sibling (get_company_open_jobs) is an unrelated domain, so no disambiguation is needed.

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 implies when the tool applies but never says so explicitly. 'Single domain' and 'No browser JavaScript execution' are meaningful constraints that steer selection (no JS-rendered detection), yet there is no explicit when-to-use/when-not framing or named alternative for the JS-rendered case.

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

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

Annotations only declare readOnlyHint and openWorldHint; the description adds genuinely new behavioral context: a hard cap of 300 jobs per call, the diff/known_job_ids mechanism, and the billing rule that a missing board, an empty board, or a downed board API is not charged. These are exactly the operational traits annotations cannot convey.

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-loads the core purpose and the returned fields before moving to the diff workflow and the billing caveat. Dense and largely waste-free, though the long first sentence packs a lot and the billing clause could be its own crisp line.

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?

With no output schema, the description compensates by enumerating return fields (titles, departments, locations, remote flag, salary when published, tech keywords) and documents the 300-item limit plus the empty/down-board edge cases. Nothing an agent needs to call it correctly is missing.

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 description coverage is 100%, so domain, diff_only, and known_job_ids are already documented in the schema (including diff_only's dependency on known_job_ids). The description restates that dependency and adds the 'new and closed job IDs' framing, but supplies no format or syntax detail beyond the schema, so baseline 3 applies.

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+resource ('Open jobs for a company domain') and enumerates the exact sources (Greenhouse, Lever, Ashby, Workable, Recruitee, SmartRecruiters) plus the fields returned. An agent immediately knows this retrieves public job-board postings for a domain, which is wholly distinct from the unrelated sibling detect_website_tech_stack.

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?

Gives concrete workflow guidance: pass known_job_ids from an earlier call to get new and closed IDs, and use diff_only for only the new jobs. There are no alternative tools to route away from, so the absence of explicit exclusions is not a gap, but it stops short of stating when a caller should prefer a full pull vs. a diff.

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