save_answerAdd or replace a screening answer in the answer book ('What is your notice period?' → '1 month'). Applications already waiting on that fact are completed and sent in the background. Only save what the person actually stated.
| Name | Required | Description | Default |
|---|---|---|---|
| kind | No | text | |
| answer | Yes | ||
| options | No | For select questions: the choices the form offers. | |
| question | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses behavioral traits beyond the annotations: replace/overwrite semantics, the background side effect of completing and sending waiting applications, and a fidelity constraint ('Only save what the person actually stated'). These add significant context beyond the all-false 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?
Three focused sentences with no redundancy. The core action and example are front-loaded, the side effect earns its sentence, and the constraint earns its sentence.
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?
The description covers the main action, side effects, and a correctness constraint, but omits guidance on how to fill optional parameters like kind and options, and does not mention return behavior. With all-false annotations and no output schema, an agent must infer nontrivial parameter usage.
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 only 25%, so the description must compensate for undocumented parameters, but it only illustrates question and answer. The kind enum and options array semantics are left entirely to inference, making correct invocation for select/number/boolean cases uncertain.
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 states a specific verb ('Add or replace') and resource ('screening answer in the answer book'), with an illustrative mapping from question to answer. It is clearly distinguishable from sibling tools like list_saved_answers and delete_saved_answer.
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 implies usage by explaining the answer book concept and the background effect on waiting applications, but it never explicitly says when to prefer this tool over related alternatives like answer_screening_question. There are no exclusions or alternative-route hints.
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.