Send API Request

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

The description adds substantial behavior beyond the sparse annotations: non-2xx responses return structured status/body data instead of MCP tool failure, sensitive headers/cookies/URL tokens/JSON body fields are masked, and environment-specific method restrictions are disclosed. This materially changes how an agent interprets results and plans calls, and nothing contradicts the 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?

Four sentences, front-loaded with the core action and mode distinction, followed by the troubleshooting use case, environment restrictions, and behavior notes. It's dense but every sentence earns its place; the last sentence packs two behaviors (error handling and masking) into one clause, slightly reducing scannability.

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 (11 params, two modes, environment-dependent behavior) and the existence of an output schema, the description covers the critical non-obvious behaviors: structured non-2xx responses, masking, and per-environment method rules. Minor gaps remain, such as not explaining that saved request scripts run or elaborating on the mutation implications, but annotations (readOnlyHint=false) partially cover that.

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%, with each parameter already documented (e.g., timeoutMs defaults to 60000ms, requestId should be omitted when sending method/url directly). The description adds the two-mode framing and groups parameters as method/url/headers/query/body, but the schema already carries most of the semantic weight, so the description's added value is marginal.

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 states a specific verb ('Sends') and a clear resource (API requests) with two precise modes: replaying a saved request by requestId or sending an ad-hoc request via method/url/headers/query/body. This distinguishes it from the sibling CRUD tools (create_request, update_request, delete_request, get_request), which manage request definitions rather than execute them.

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 description gives an explicit use case ('Use it to reproduce API failures during agent troubleshooting') and explains environment-specific constraints (dev allows all methods, test marks mutating as write risk, prod restricts to GET/HEAD/OPTIONS). It doesn't explicitly name alternatives or say when not to use it, but the execution-vs-management distinction from siblings is clear enough.

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