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

Annotations cover the safety profile (readOnlyHint=false, idempotentHint=true, destructiveHint=false), and the description adds substantial context beyond them: the X-NW-User-Key sign-scope requirement, stale-hash refusal behavior, consent lapse on rules change, that caps are never exceeded, and the custody assurance ('NightWatch never holds your 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?

Front-loaded with the purpose, then prerequisites, then failure modes; no sentence is filler. It is a dense single block rather than segmented, but every clause carries operational value.

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, the description covers auth, prerequisites, failure behavior, caps semantics, and custody. Nothing an agent needs to invoke it correctly 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?

At 80% schema coverage the baseline is 3, but the description goes further: it clarifies that max_order_usd and max_leverage are YOUR caps that plans never exceed, that rules_hash must come from forge_signals and a stale value is refused, and that account_address is your checksummed 0x address. This resolves the ambiguity of who owns the caps.

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+resource ('Consent to mirror a Forge vault's signals into YOUR OWN account') and even names the endpoint. An agent can distinguish this from the revoke sibling and from forge_signal_plan without opening a schema.

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 clear preconditions (required args, sign scope, cannot mirror your own vault) and the lifecycle rule (consent lapses if rules change; consent again to the new hash). It stops short of explicitly routing the agent to alternatives like forge_mirror_revoke, so no exclusions are stated.

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