JobsRadar

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

With no annotations, the description carries the full burden and does well: it discloses the 'data_as_of' freshness field, the page cap and 'truncated' flag for SmartRecruiters, and the 1-credit cost. It omits auth requirements and general rate-limit behavior, so it is not fully complete.

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?

Four tight sentences with no filler; the purpose and accepted input forms are front-loaded, and the edge-case behavior (truncation, cost) is appended where it belongs.

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 read-only lookup with no output schema and no annotations, the description covers the key return semantics (data_as_of, truncated) and cost, which is most of what an agent needs. Auth/permission context is the only notable omission.

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 all three parameters are already documented, including the provider enum and its Workable 429 caveat. The description's mention of board slugs and ATS detection largely restates what the schema says, so baseline 3 is appropriate.

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 with scope: 'Returns all public postings for one company,' plus the multi-ATS detection behavior. It does not explicitly distinguish itself from the sibling search_jobs, so an agent must infer the company-scoped vs. cross-company split.

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 tells the agent what input is acceptable ('a tracked company name, or any board slug') and that detection is automatic, which implies when this tool fits. However, there is no guidance on when to prefer search_jobs or list_supported_companies instead.

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?

With no annotations, the description carries the full burden and does well: it discloses the cost profile ('Free to call') and the data window ('last 30 days'), which are genuine behavioral facts beyond the schema. It does not mention auth requirements or rate limits, so it falls short of a 5.

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 tight sentences with the contents front-loaded and the cost note appended. Every clause earns its place; nothing is repeated from the schema or 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?

There is no output schema, so the description must hint at the return shape, and it does by naming the three returned fields and their window. No annotations exist either, and the 'free to call' note covers the main behavioral concern. Minor gap: no mention of formatting or staleness.

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?

The tool takes zero parameters, which is the baseline-4 case. The description adds no parameter semantics because none exist, and needs none.

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 (get) and resource (usage) and enumerates exactly what is returned: plan, remaining credit balance, and call volume over the last 30 days. It is clearly distinguishable from the invoice-oriented siblings (extract_invoice, generate_invoice, validate_invoice, describe_coverage).

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?

No explicit when-to-use or when-not-to-use guidance and no named alternatives, but for a zero-parameter, cost-free read tool the implied usage ('check your balance/usage') is reasonably self-evident. It provides no routing conditions.

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?

With no annotations, the description carries the full burden, and it does disclose the cost ('Light read: costs 0.2 credit') and the return shape (grouped by ATS). It stops short of describing pagination or result size, but for a small static directory this is solid disclosure.

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 tight sentences: purpose first, routing second, cost and slug convention last. Every sentence earns its place with no filler.

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?

No output schema exists, but the description compensates by describing the grouping, the slug convention, and the exceptions under 'slugs', plus the credit cost. 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% and the single provider enum is fully self-documented, so the baseline is 3. The description's slug explanation describes output values rather than parameter behavior, adding little to the `provider` filter itself.

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 ('Returns the curated directory of companies whose public job boards are tracked') plus the organizing principle (grouped by ATS). This distinguishes it cleanly from search_jobs and get_company_jobs.

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?

'Use it to pick names for search_jobs' explicitly names the sibling and the condition that selects it, turning this into a discovery step for search_jobs. 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?

With no annotations the description carries the full burden, and it does substantial work: deduplication/normalization behavior, 15-minute refresh cadence, the meaning of 'data_as_of', the 'boards_truncated' truncation signal and a stated cost of 1 credit. It omits auth requirements and any rate-limit behavior, keeping it short of a 5.

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?

Five tight sentences, each carrying distinct information (scope, filters, default behavior, freshness field, truncation field, cost), with scope front-loaded. Nothing is redundant or padded.

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?

There is no output schema, and the description proactively explains two return fields ('data_as_of' and 'boards_truncated') plus the dedup/normalized shape, which covers the main ambiguity for a search tool. It doesn't describe the full result record or pagination/limit interaction, leaving a small 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 description coverage is 100%, so the schema already documents all six parameters (limit, location, remote_only, posted_after, title_keywords, companies). The description's filter list adds no syntax or format detail beyond what the schema provides, 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 (Searches) and resource (open roles across many company job boards) and adds 'in a single call' plus 'deduplicated, normalized list', which implicitly distinguishes it from the single-company sibling get_company_jobs. An agent can tell what this returns without opening the 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?

Explains the key branch: 'Without a company list it searches the whole tracked directory', and enumerates the available filters. It gives clear context for invocation but never explicitly names get_company_jobs as the alternative for a single company, so routing between siblings is left partly to inference.

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