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

Goes well beyond the annotations by explaining per-ATS mechanics (Greenhouse/Lever use a documented detail endpoint where HTTP 404 = closed; Ashby has no per-job endpoint so the board is fetched and searched, method 'board_listing'). It also flags retryable errors (HOST_BLOCKED, NETWORK_ERROR) and an important semantic caveat that 'open' means published, not actively hiring.

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?

Labeled WHAT/WHEN/WHEN NOT/BEHAVIOR/COST/RETURNS/PARAMETERS/EXAMPLE blocks are densely front-loaded with zero filler, and the one-line example anchors the calling convention. Verbose in raw length but every line carries unique 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?

Although an output schema exists (so returns need not be restated), the description nevertheless names the return fields and the failure modes, plus cost and ATS-specific behavior. An agent has everything needed to call it correctly and interpret the result.

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% and each parameter is already documented, so the baseline is 3; the description earns above that by stating the either/or contract and the precedence rule ('jobKey wins when both are given'), which the schema does not express. It does not add format/syntax detail beyond the schema's examples.

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?

Starts with a specific verb+resource+scope ('Re-check ONE job on the employer's ATS right now') and explicitly reports the binary outcome (open/closed). It is immediately distinguishable from siblings like jobs_get_board and jobs_search_companies.

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?

Contains explicit WHEN ('before applying, alerting or contacting about a specific job you got earlier') and WHEN NOT sections that name the alternative tools and the condition that selects them (listing vs. bulk-checking with confirmOpen, paid). Nothing is left to inference.

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 already declare read-only, idempotent, non-destructive, open-world, so the bar is lower, yet the description still adds substantial behavior: the resolution order, robots.txt respect, <=3 careers pages, refusal of private/internal IPs, at most 6 ATS API GETs, stopping at first hit, and no caching/storage. This is far beyond the annotations; the only omission is rate-limit/backoff behavior.

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?

Well front-loaded with labeled WHAT/WHEN/WHEN NOT sections and a concrete example, and every section carries information. It is long, and 'COST: Free' duplicates the title's '(free)' label, a minor redundancy in an otherwise dense block.

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?

Despite an output schema existing, the RETURNS section adds value the schema cannot: the 'via' enum values, the confidence semantics, and specifically that a slug_probe hit is only 'medium' and may be the wrong company. Combined with cost, network constraints and meta.notes, an agent has everything needed to call and interpret this tool.

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 a baseline of 3 applies, but the PARAMETERS section adds genuinely new meaning: the three accepted input forms (board URL, domain/URL, plain name) trigger different execution paths, which the schema's flat string description does not convey. The worked example further anchors expected input/output.

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?

Opens with a specific verb+resource ('Resolve a company name, domain or careers/board URL to its public job board(s)') and immediately scopes it to Greenhouse/Lever/Ashby. It explicitly distinguishes itself from the siblings jobs_get_board and jobs_search_companies, so an agent can route without opening any 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 WHEN and WHEN NOT sections give explicit conditions and name the alternatives: use jobs_get_board when you already have ats+slug, jobs_search_companies for bulk paid lookups, and it states the ATSs it cannot find (Workday, Workable, Recruitee, LinkedIn). Nothing is left to inference.

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 cover the safety profile, but the description adds substantial context annotations cannot: local execution, one GET to a documented host, a 403/429 session kill-switch with HOST_BLOCKED, Lever's 1 s Crawl-delay spacing, no token/storage, and first_seen_at/change semantics. This is rich disclosure beyond the structured hints.

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?

Heavily structured and front-loaded with WHAT/WHEN/WHEN NOT, so an agent gets routing information immediately. It is dense and the RETURNS block partially restates fields that the output schema already carries, which is the main reason it is not a 5.

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 12-parameter read tool with full schema coverage and an output schema, this covers the remaining gaps: filter composition rules, paging volatility when the board is edited, supported/unsupported ATSs, and rate-limit behavior. Nothing needed 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 coverage is 100%, so the baseline is 3, but PARAMETERS adds cross-parameter semantics not present in any single schema field: filters are AND-ed while values within a filter are OR-ed, titleIncludes matches whole words, countries drops unmatched rows, and postedWithinDays drops null-dated rows. Only slight overlap with the schema's per-field docs, hence 4 rather than 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?

The WHAT line names a specific verb+resource (fetch every job published on ONE company board from its official public ATS API) plus the scoping constraint (one board, supported ATS list). It explicitly distinguishes itself from jobs_search_companies (many companies/history) and jobs_find_board (board discovery).

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?

WHEN gives the precondition (you know ats + slug), WHEN NOT enumerates the alternatives and the exact tools to use instead (jobs_search_companies for scale/history, jobs_find_board for unknown boards), and it rules out unsupported ATSs explicitly.

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 already cover safety (readOnly, idempotent, non-destructive, closed-world), but the description adds substantive behavior beyond them: offline static list with no network call, the free cost, and the staleness caveat that jobs_at_verification is a snapshot from verified_at. That staleness warning is exactly the kind of non-obvious trait that prevents misuse.

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 WHAT/WHEN/WHEN NOT/BEHAVIOR/COST/PARAMETERS/EXAMPLE structure is front-loaded and scannable, with no wasted clauses. The RETURNS block partially restates the output schema, which is the only mildly redundant element.

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 zero-required-parameter, read-only list tool with an output schema and full annotation coverage, the description supplies everything an agent needs: scope, exclusions, chaining guidance, cost, and the staleness caveat. Nothing material 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 coverage is 100%, so the baseline is 3, but the description adds genuine meaning: 'ats narrows the list; omit it for all three systems' clarifies the default behavior, and 'feed ats + slug of any item straight into jobs_get_board' documents the intended chaining usage that the schema cannot express.

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 ('List the bundled starter list of company job boards') plus the scope of what was verified (official ATS APIs) and the fields returned. It is immediately distinguishable from jobs_get_board (live data) and jobs_find_board (resolution of arbitrary names).

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?

Explicit WHEN ('to pick companies to scan, or to know which names jobs_find_board resolves instantly') and WHEN NOT ('live job data (jobs_get_board) or companies not in the list (jobs_find_board)'), naming both alternatives and the condition selecting each.

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 provide readOnlyHint/openWorldHint/idempotentHint/destructiveHint, but the description adds a lot beyond them: requires APIFY_TOKEN, runs in the user's own Apify account, waits up to 300 s, persists history in a named key-value store, and documents politeness controls (ATS APIs only, 403/429 kill switch, robots.txt). Detailed pay-per-event cost breakdown and the 'each call starts a new billed run' caveat are disclosed. Nothing here contradicts the annotations.

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 labeled sections (WHAT/WHEN/WHEN NOT/BEHAVIOR/COST/RETURNS/PARAMETERS/EXAMPLE) make it skimmable, and for an 18-parameter paid tool every section earns its place. The cost and 'one run, fetch your pages' guidance prevent classic misuse.

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?

Given the complexity (18 params, paid per-event billing, external Actor run), the description covers purpose, routing, auth, cost, behavior, return-row types, and a concrete example. An output schema exists, yet the RETURNS section still usefully summarizes row kinds. 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 coverage is 100%, so 3 is the baseline, but the description adds cross-parameter semantics the schema cannot express: at least one of companies/boards/useSeedList is required even though all are marked optional (else INPUT_EMPTY, unbilled), onlyNew depends on stateStoreName matching the prior run, and limit/offset page rows locally while every call incurs a new billed run. These are meaningful additions, though several per-parameter details (remote, postedWithinDays, excludeStale) are left to the schema.

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 precise verb+resource: running the fairquery/company-jobs-feed Actor over many companies or boards, including discovery, filters, and history. It explicitly contrasts scope with siblings jobs_get_board (single board) and jobs_check_open (single job), so an agent can distinguish it without opening any 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 WHEN and WHEN NOT sections name the exact conditions and the free alternatives: use it for monitoring a company list, history/closed/repost signals, or many boards; avoid it for one board (jobs_get_board, free) or one job (jobs_check_open, free). No inference is required.

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