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

Annotations indicate mutation (readOnlyHint: false) and non-idempotency, but description adds critical behavioral context: 8-credit cost model, synchronous execution, and return format (array with rationale). Does not contradict annotations. Could mention error handling or rate limits for a 5.

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?

Seven information-dense sentences with zero waste. Front-loaded with core purpose and cost, followed by return value, features, prerequisites, and workflow guidance. Every sentence 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 no output schema exists, description adequately covers the return value structure ('array of interview questions with rationale'). Prerequisites, cost, synchronous nature, and sibling relationships are fully documented for this 5-parameter workflow tool.

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?

With 60% schema coverage, description compensates well by explaining pressure_level semantics (supportive/standard/aggressive), jd_text purpose (role-targeted questions), and prerequisite sources for context_id/candidate_id. Only gap is num_questions, which has schema constraints but no descriptive text.

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 specific verb (Generate) + resource (interview questions) + scope (tailored to candidate's profile). Explicitly distinguishes from sibling tool 'atlas_interview_followup' by stating this is for initial generation while the sibling is for follow-up probing.

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?

Explicitly names the alternative tool for subsequent steps ('use atlas_interview_followup for follow-up probing'). Clear prerequisites stated: requires context_id from atlas_list_contexts and candidate_id from atlas_list_candidates. Also clarifies optional jd_text sourcing.

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