Register a canary (operator session required)

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

Goes well beyond the annotations: it discloses the required Authorization: Bearer <Desk session> and that the session wallet is the operator, that private material is refused before validation, the freshness rule for bait keys, the two-minute chain polling cadence plus pushed ingest, that fires only go to the caller's canary log with nothing published, and a 25-canary shadow-period cap. These are exactly the side effects, auth needs, and limits an agent cannot infer from readOnlyHint=false / idempotentHint=true.

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 first sentence front-loads purpose, required fields, and auth, which is good, but the remainder is a single dense block mixing operator guidance, refusal rules, polling mechanics, and quota trivia in one paragraph. Much of it earns its place, yet the illustrative canary examples and repeated restatement of the public/private rule could be trimmed or split.

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 a mutation tool with no output schema and a nested object parameter, the description covers auth, refusal behavior, polling cadence, and operational limits thoroughly. It is slightly incomplete on the return side: it never says what a successful registration returns, and canary_id (present in the schema) is not mentioned in the prose.

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 real semantics the schema lacks: it lists the valid kind values (address|key|url|apikey|tool|x402) and the full watch trigger vocabulary (nonce, code, permit, siwe, inbound_transfer, http_hit, api_use, tool_call, x402_request), which are enums absent from the schema. It falls short of 5 only because it never explains which fields pair with which kind beyond a brief parenthetical.

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 ('Register the public part of a decoy you planted') and enumerates the accepted kinds, so the agent immediately knows this creates a canary record rather than reading one. It is clearly distinguishable from the sibling canary_status, which is a status/read tool.

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 strong context for when to use it ('a canary is a decoy you plant where only an intruder or a misled agent would read it') and what to register (the PUBLIC part only, one target per canary). It does not explicitly name an alternative tool or state when not to use this one, but the conditions that select it are unambiguous.

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