http_patch

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

Annotations already declare idempotentHint=false and destructiveHint=true, so the bar is lower. The description adds genuine value by explaining WHY idempotency isn't guaranteed — "depends on the server's patch semantics" — which is beyond the bare annotation. But it contributes little else: no side-effect scope, auth requirements, or response-behavior disclosure.

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?

Roughly three short clauses — action, usage context, and one critical caveat — with zero filler. The core purpose is front-loaded and every sentence earns its place. This is appropriately sized given that the schema carries all parameter detail.

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 powerful open-world HTTP tool with 14 parameters, nested objects, and no output schema, the description is thin: it omits response-format hints, truncation/error behavior, and explicit when-not-to-use guidance. The unusually rich schema (defaults, bounds, per-param semantics) and annotations compensate substantially, keeping it adequate but not 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 description coverage is 100%, so the baseline is 3. The description adds nothing about parameters — all 14 (url, body, headers, retries, body_json, allow_private_hosts, etc.) are documented entirely in the schema with defaults and bounds. No bonus, no penalty beyond baseline.

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?

"Perform an HTTP PATCH" states a specific verb and resource, and "Use for partial updates" pins down the exact use case that separates it from siblings like http_put (full replacement) and http_post (creation). The idempotency caveat further differentiates it from http_put, which is conventionally idempotent.

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?

"Use for partial updates" is a direct, clear usage directive, and the idempotency warning functions as a caution against relying on safe retries. However, it never names alternatives (e.g., "use http_put for full replacement") or states explicit exclusions, so it stops short of a 5.

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