Call API Endpoint

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

Annotations already mark this as destructive and non-idempotent. The description adds valuable behavioral context by disclosing the two-phase confirmation (preview then execute with confirmed=true) and the base URL resolution order (spec, env var, or parameter), which the annotations do not convey.

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 no wasted words. The primary action is front-loaded, followed by the most important behavioral nuance (confirmation) and the base URL precedence. Every clause contributes meaningful information.

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 the tool's complexity (8 parameters, two-phase confirmation, no output schema), the description covers the critical flow and URL resolution. It does not describe response shapes or failure modes, but for an execution tool the confirmation mechanism is the most important context and is well described.

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?

The schema describes all 8 parameters with 100% coverage, so baseline is 3. The description additionally clarifies the semantics of two key parameters: 'confirmed' controls preview vs. execution, and 'base_url' can override other sources. This adds meaning beyond the schema without repeating 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 begins with 'Execute an actual HTTP request to an API endpoint,' using a specific verb and resource that clearly distinguishes this tool from sibling tools that only read or load spec data. It also mentions the two-phase confirmation, which adds to its unique identity.

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?

The context makes it obvious this is the tool for making real API calls versus the read-only/spec-management siblings. It does not explicitly spell out 'use this instead of swagger_get_endpoint when you want to send a request,' but the wording 'actual HTTP request' implies that distinction effectively.

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