list_blocking_questionsQuestions employers asked on applications that are stalled until this account answers them, grouped by application, each with a suggested answer drawn from what the person answered before. Answer with answer_screening_question.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Maximum number of applications to expand. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and idempotentHint, so the description correctly aligns with them. It adds meaningful behavioral detail beyond annotations: results are grouped by application, limited to blocking/stalled questions, and include suggested answers derived from prior responses.
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?
One dense sentence with no wasted words, front-loading the core purpose and ending with a clear actionable pointer to the sibling tool. Every clause contributes to selection or invocation.
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 simple read-only list tool with one self-documenting optional parameter, the description fully covers what the agent needs: what is listed, how it is organized, what each item contains, and what to do next. No output schema exists, but the return semantics are sufficiently described.
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%: the only parameter, limit, has a clear description plus default/min/max. The description adds no parameter-specific meaning, which is acceptable since the schema already handles it.
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 ('list') and resource ('blocking questions'), and clarifies these are employer questions, grouped by application, with suggested answers. It also names the answering sibling, distinguishing this read/list tool from actions like answer_screening_question.
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 makes the applicability clear: questions stalled until this account answers them, with a routing instruction to answer using answer_screening_question. It does not explicitly enumerate when-not conditions, but the context is enough to select this over siblings.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Tool purposes are generally distinct and well-described, but a few clusters overlap in function: answer_screening_question vs save_answer both write to the answer book, get_my_profile vs get_account both report plan status, and the CV preview/sent-CV/base-CV tools could be confused. The detailed descriptions mitigate most misselection, so this is only a minor issue.
The set almost uniformly uses snake_case verb_noun names like list_, get_, update_, create_, delete_, and start_/stop_. Minor deviations such as login, describe_what_i_want, and the get_my_* vs list_* alternation prevent a perfect score, but the overall pattern is predictable and readable.
49 tools is far above the 25+ threshold and will burden agent tool selection even though many are legitimate single-purpose operations. Several groups could be consolidated—billing links, API-key management, and the CV PDF family—without hurting clarity.
The surface covers the full lifecycle: account creation/auth, profile and CV, targeting, matching, apply runs, screening answers, tracking, billing, export, and deletion. Minor gaps remain, such as no application-level detail/withdrawal endpoint and no direct way to save a parsed CV without re-uploading, but agents can work around them.