update_guardrail

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

Annotations declare readOnlyHint=false and idempotentHint=false, but the description adds genuinely non-obvious behavior beyond them: the update creates a new version, takes effect immediately for dependent configs, and returns id/slug/version_id. This versioning side-effect is exactly the kind of context structured fields cannot convey. No contradiction with annotations.

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 sentences with zero filler: purpose and sibling contrast first, then the versioning consequence and recommended pre-step, then the return contract. Every clause earns its place and the most decision-relevant information is front-loaded.

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 mutation tool with nested objects and an output schema, the description covers purpose, sibling routing, a behavioral warning (immediate effect on dependent configs), a recommended pre-step, and the return payload. The output schema covers return structure, so nothing an agent needs to invoke this correctly is missing.

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 documents all four parameters richly, including the security caution on forwarded headers. The description only echoes the parameter categories (name, checks, actions) without adding syntax or format detail. This meets the baseline for high schema coverage but adds no parameter-level value beyond it.

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 opens with a specific verb+resource+scope: 'Update a guardrail's name, checks, or actions', and immediately differentiates itself from siblings ('unlike create_guardrail which registers a new one or delete_guardrail which removes it'). An agent can distinguish this from create/delete/get/list variants without opening the schema.

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 alternatives and the condition that selects them: create_guardrail for registration, delete_guardrail for removal. It goes further by prescribing a workflow step ('review list_guardrails first') because updates create a new version that affects dependent configs. This is direct when-to-use and when-not-to-use guidance.

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