Search openings at named companies

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

The description goes well beyond the annotations by disclosing request costs (3 requests for found, up to 9 for resistant, 1 second each), exact wording requirements for Lever filters, local vs server-side filtering behavior, per-company limit application, and pagination depth for posted_within_days. This provides important operational context that annotations alone would not 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?

Every sentence in the description carries unique, actionable information. It is dense but not verbose, and the purpose is front-loaded in the first sentence. There is no wasted text; all details about costs, filtering, and pagination are necessary for correct use.

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 tool's complexity (14 parameters, pagination, rate limits), the description covers the key behavioral aspects thoroughly: rate costs, exact wording constraints, local vs server-side filtering, per-company limit semantics, and pagination. The output schema (not shown) presumably handles return fields, so the description need not duplicate that; it fills the gaps around usage costs and filter behavior comprehensively.

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?

Although the schema covers 100% of parameters, the description adds critical behavioral semantics: companies are converted to site names, certain params require exact Lever wording, others are applied locally, limit is per company, and posted_within_days walks multiple pages. This meaningfully enriches the schema definitions and explains edge cases.

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 description opens with a specific verb+resource: 'Search the openings published by named companies on Lever.' This clearly distinguishes it from sibling tools like get_job (which fetches a single job) and resolve_company (which resolves company names). The scope is precise about searching across multiple named 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?

It provides clear context about the domain (Lever) and how parameters behave differently (server-side vs local filtering). It does not explicitly state when to use this tool over get_job or resolve_company, but the scope is obvious from the description. There is no exclusionary guidance, but the context is strong enough to infer appropriate use.

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