Issue Capability Sink Challenge

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

Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description usefully adds the return payload (SinkChallenge + challenge_hash) and the binding role, but says nothing about the private-key handling, expiry semantics, or what happens on replay — notable for a tool that signs with a caller-supplied key.

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 short sentences, front-loaded with the identity of the operation and then its return and role. The trailing 'Search keywords' line is padding but cheap, and nothing else is wasted.

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 does the right thing by naming the returned SinkChallenge and challenge_hash, and it situates the call in a larger gateway evaluation flow. However, for a 7-parameter cryptographic tool with nested objects, it omits prerequisites (sink key possession, ordering relative to sign_effect/evaluate_authority) and any expiry/freshness context.

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 71% and the description contributes zero parameter meaning: validity_seconds and required_policy_freshness have no schema descriptions and nothing in the prose explains them, while 'canonical action statement' merely echoes the action field's own description. The description does not compensate for the coverage gap.

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 gives a concrete verb and resource: the sink 'issues a signed canonical action statement' and returns a SinkChallenge with its challenge_hash. That is more than a restatement of the name, though the sibling tools in the aps_capability_* family (evaluate_authority, mint_receipt, sign_effect) are never named or differentiated.

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?

It states the downstream role ('bind the gateway's later policy evaluation to a specific action the sink authored'), which implies where this fits in a flow, but gives no explicit when-to-use, no prerequisites, and no alternatives. 'Search keywords' is retrieval metadata, not usage guidance.

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