noticer_run_receipt

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

Annotations declare readOnlyHint=false, yet the description twice asserts 'Reads only' while also saying it 'Starts observation and returns a check identifier' — i.e. it creates server-side state. This is a direct contradiction that could lead an agent to treat a state-creating call as side-effect free. The otherwise useful disclosures (booleans are caller assertions not proof of consent, future USD 1 evidence access, 3-second polling floor) do not offset the contradiction.

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?

The critical gating condition is front-loaded, which is good, but the text repeats itself ('it never pays or performs or repeats the original action' vs 'It never pays or performs the downstream action') and multiplies jargon where one plain sentence would do.

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 detail is covered, and the commercial/consent context is unusually well conveyed. Still, for a 4-parameter open-world tool it omits the meaning of check_label and never tells the agent which sibling (noticer_receipt_status, noticer_get_verified_receipt) continues the flow after the check identifier is returned.

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 carries the full burden. It does explain that obligation_hash is the saved obligation hash and that both booleans must reflect explicit owner approval and are assertions rather than proof, but it never mentions check_label at all — one of four required parameters is entirely 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?

States a specific action and resource: observe a saved public JSON condition tied to a frozen scope, starting the observation and returning a check identifier. The verb and effect are clear, though the jargon ('saved public JSON condition', 'frozen scope') is opaque and it never names how it differs from noticer_prepare_receipt or noticer_receipt_status.

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 explicit preconditions ('only after approval of the exact frozen scope and confirmation notice', 'Supply its saved obligation_hash') plus operational rules: poll no more often than 3 seconds, evidence access may later need a separate USD 1 approval. It lacks an explicit when-not or a pointer to noticer_receipt_status for the polling it references, so it falls short of 5.

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