cap_check

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

With no annotations, the description carries the full burden and does reasonably well: it discloses that the function is local and pure (no external side effects), that the result is ALLOW/DENY, and that cap_token is only included on allow when CAP_TOKEN_SECRET is configured. It omits error/deny-case behavior and any latency or determinism caveats.

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 dense sentences, front-loaded with the core purpose and followed by output behavior and the required follow-up call. Nearly every clause earns its place; the parenthetical HTTP equivalence is useful rather than filler.

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?

With no output schema, the description must describe returns and it partially does (ALLOW/DENY plus conditional cap_token). It remains incomplete on the undocumented `card` parameter and on failure modes, leaving gaps an agent would need to resolve before calling correctly.

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 0% across three parameters, so the description must compensate, and it only partially does. It restates the action enum and ties action to the downstream token flow, but the `card` parameter is never mentioned and the `cap` parameter's format or source is not explained.

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 (ALLOW/DENY) and resource (a published cap string for an action), and notes it is a local pure function equivalent to POST /cap-check, which helps an agent map it to a known HTTP operation. It does not fully define what a 'cap string' is, but the operation itself is unambiguous.

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?

Gives one concrete conditional workflow rule: spend/send actions must subsequently call cap_token_check before the hop. However, it never explains when to prefer this over the sibling cap_preflight, nor when-not to use it, so routing between the two cap-related tools is left to inference.

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