list_open_jobs

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

With no annotations provided, the description carries the full behavioral burden and meets it admirably. It discloses the refusal-over-guessing salary policy with specific edge cases (hourly rate, ambiguous currency, dual-currency bands yield no figure), that salary_text preserves the employer's raw text, that verify_url points to the employer's own advert, and (in the include_description schema field) that email addresses and phone numbers are stripped. These are non-obvious behaviors an agent needs to set expectations correctly.

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 purpose is front-loaded in the first sentence, and the prose is efficient. The salary paragraph is the longest but earns its space because the refusal behavior is genuinely non-obvious and critical to trust calibration. It is slightly verbose as three prose paragraphs where a scannable list would do, but every sentence carries information, so no waste.

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 having no output schema and no annotations, the tool is well covered: return fields are enumerated, salary refusal behavior is specified, company input formats live in the schema, and PII stripping is noted. The only gaps are pagination behavior (limit exists up to 1000 but continuation is undocumented) and error handling for unknown companies — minor omissions that prevent a 5.

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 schema's own parameter descriptions are rich (company accepts board name, careers URL, or system:name; include_description explains why it defaults off). The description adds complementary value by explaining what the tool returns for a given call, but it stays at the output/behavior level rather than clarifying parameter semantics directly — so it slightly exceeds the baseline-3 for full coverage without doing the schema's job.

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 opening line states a precise verb and resource ('Every open job at one company, read from its own careers system') that immediately distinguishes it from find_company_board (locating a board) and compare_companies (comparing enterprises). Listing the exact return fields (title, department, location, employment type, salary range, verify_url) removes all ambiguity about what the tool yields.

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 firmly scopes usage to a single company ('Every open job at one company'), which is clear context, and the 'own careers system' plus verify_url language signals data provenance. However, it never names the sibling alternatives or states when NOT to use it (e.g., no explicit 'to compare companies, use compare_companies'), leaving the routing to inference rather than stating exclusions.

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