http_request

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

Beyond the annotations (which only say non-read-only, open-world, non-idempotent, non-destructive), the description discloses that headers are redacted, the body is truncated, and results are prefixed PASS/FAIL when assertions are supplied — genuinely useful output-shape context. It omits how truncation is bounded and whether auth/cookies are forwarded, which would complete the picture for an open-world network tool.

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?

Three compact sentences, front-loaded with what the tool does and what it returns, followed by the assertion options. The parenthetical example for expect_json earns its space; nothing is redundant. Slightly dense but well ordered.

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?

An output schema exists, so return values need not be described, and the assertion semantics are covered. However, with 13 parameters at 0% schema coverage, the undefined ones (verify_tls, follow_redirects, timeout units, body vs json_body precedence) are material gaps an agent would hit in real calls.

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 0%, so the description must carry parameter meaning, and it does for only 4 of 13: expect_status, expect_json (with a concrete path->value example), expect_contains, and max_latency_ms. Nothing explains method, body vs json_body, params, headers, timeout units, verify_tls, or follow_redirects — the highest-risk ambiguous pairs go undocumented.

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?

Specific verb+resource ("Send an HTTP request") plus an explicit account of what is reported (status, timing, redacted headers, truncated body). It also carves out scope ("localhost and private addresses allowed"), which implicitly separates it from web_fetch, but never names that sibling, so an agent must infer the boundary.

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?

Usage is only implied: the assertions section suggests this tool is for probing/validating endpoints rather than fetching content for reading, and the localhost note hints at local service testing. There is no explicit when-to-use versus web_fetch, api_load_test, or check_tcp_port, and no stated preconditions or exclusions.

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