Waive Health Gate

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

Annotations already declare a non-read-only, non-destructive, idempotent, closed-world mutation; the description adds genuinely non-obvious context on top: that waiving bypasses a safety gate, that the server stores the waiver verbatim and does not verify who made the decision, and that the stored waiver is meant to represent an explicit user decision. It doesn't cover repeat-call behavior or the response shape, keeping it at 4 rather than 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?

Front-loads the purpose in the first sentence, then moves to behavioral trust model and finally parameter semantics, with no filler sentences. It is dense and slightly run-on across five sentences, but each one adds information an agent needs.

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 4-required-param mutation with no output schema, the description covers trigger, trust model, and all parameter meanings, and annotations carry the safety profile. Minor gaps remain around idempotent repeat behavior and what the stored waiver looks like on return.

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 0% schema description coverage the description must carry all parameter meaning, and it does: kind is 'base' or 'application' (matching the enum), key is the resume slug or application id, reason is the user's stated justification, and gate_id is pinpointed as the gates[].id value from get_health_report. Every required parameter is disambiguated beyond the bare schema.

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 precise verb+resource (waive a health gate) and anchors it to a concrete trigger: the fatal-health-gate 409 from create_tailoring_session. It also names the sibling tools it interacts with (create_tailoring_session, get_health_report), so an agent can distinguish it from nearby tools like unwaive_health_gate or run_health_check.

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?

Gives a clear when-to-use condition (only as an escape hatch after create_tailoring_session returns a fatal-health-gate 409) and explains how to obtain the required gate_id from get_health_report. It never explicitly names unwaive_health_gate as the reverse operation or states when NOT to waive, so it falls just short of full routing guidance.

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