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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, and the description still adds material context: 'other hosts are refused', each call is 'metered as one execution', results are returned inline 'within about two seconds', and the agent must not resend but instead poll operation_status/operation_output. That async/timeout/security disclosure goes well beyond the structured hints.

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?

Single dense paragraph with the trigger clause front-loaded, followed by behavior, prerequisites, and the async fallback in a logical order. Every sentence carries information, though the run-on density makes it slightly harder to scan than an ideal definition.

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 an 8-parameter tool with nested objects and no output schema, the description supplies the missing pieces: what is returned (status and bounded body), the latency expectation, the async continuation path, and the security boundary. It omits guidance on deadlineAt and header usage, but those are covered by the schema, so nothing essential 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 baseline is 3, but the description adds cross-references the schema cannot express: sessionId comes from execution_session_open, operationId must be new per call, and metering ties to the call itself. It does not explain deadlineAt or efficiencyProfile, but those are documented in the schema.

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?

States a specific verb and resource ('sends a GET or HEAD request to a localhost URL') plus the returned artifacts (status and bounded body). The GET/HEAD framing implicitly separates it from localhost_send, which handles other methods, so an agent can route between 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?

Opens with an explicit trigger ('Use this when the user wants to check an approved service') and states the prerequisite sessionId source and the operationId requirement. It also prescribes the follow-up path (operation_status/operation_output) when the result is not inline. It never explicitly names localhost_send as the alternative for non-GET/HEAD traffic, so the exclusion is only implied.

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