manage_candidates

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

The description claims actions like 'recommend stage changes' (suggestions, non-destructive), but annotations set destructiveHint=true and readOnlyHint=false, contradicting the suggested behavior. No explanation of actual side effects or state changes is provided.

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 concise sentences: first lists all supported actions, second states the crucial constraint about browser storage. No redundant information; all content earns its place.

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 (4 params, nested candidates, enum actions), the description covers purpose and scope but lacks guidance on when to use each action, output details, and resolves the destructiveHint contradiction. Partially complete.

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%, so the schema already explains parameters well. The description adds a plain-language summary of the action enum but does not deepen understanding of criteria, candidates, or jobDescription beyond what the schema provides.

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 clearly states the tool manages and analyzes candidates, listing five specific actions (rank, filter, recommend_stage, compare, summarize) and explicitly stating it operates on passed-in data, not browser storage, distinguishing it from sibling tools like ats_manage_candidates.

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 clarifies that the tool works on candidate data passed in, not from storage, which is a key usage condition. However, it does not explicitly state when not to use this tool or name alternative tools for fetching or storing data.

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