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

Adds critical context beyond annotations: credit cost, execution duration (30-60s), and return value structure ('positioning snapshot, detected lens, targeted edits with trade-offs') compensating for missing output schema. Does not contradict annotations (readOnlyHint: false aligns with autonomous review creation).

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?

Four dense sentences with zero waste: action/components/cost upfront, sibling differentiation second, return values third, parameter sourcing fourth. Every clause 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?

For a complex, credit-consuming composite tool with no output schema, the description adequately covers returns, cost, timing, and prerequisites. Minor gap: does not specify error behavior or whether results are persisted/cached given idempotentHint: false.

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 80% (high), so baseline applies. Description mentions 'cv_version_id' source but largely repeats schema information. Does not significantly augment understanding of jd_text, requested_lens, or include_opportunities 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?

States specific action ('Run autonomous full CV review'), composite components ('positioning + lens detection + targeted edits + optional opportunities'), and explicitly distinguishes from the 3-step pipeline siblings (ceevee_analyze_positioning -> ceevee_get_opportunities -> ceevee_confirm_lens).

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 identifies when to use ('Alternative to the 3-step pipeline') with specific tool names, provides cost ('10 credits') and timing ('30-60s') for decision-making, and notes prerequisite steps ('cv_version_id from ceevee_upload_cv').

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