Signed evidence bundle for an address (free)

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

Goes well beyond the readOnly/openWorld/idempotent annotations: discloses that output is Ed25519-signed and offline-verifiable, that OceanAlt assumes a witness posture with no person attribution, that all data is already public with no privileged channel, and gives an explicit rate limit. This is exactly the extra context annotations cannot carry.

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-loads the deliverable and its contents, then layers in the epistemic stance and rate limit. Slightly long, and the 'witness, not a plaintiff' framing is more positioning than operational detail, but nothing is redundant.

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 usefully enumerates what the bundle contains, so an agent knows the shape of the response. Missing only guidance on error cases (unresolvable address, unknown network) and size/pagination expectations for a large bundle.

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 100%, so both address formats and the optional network field are already documented in the schema. The description adds no format syntax, defaults, or semantics beyond that, so the baseline 3 applies.

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 ('Everything OceanAlt can say about an address, in one Ed25519-signed bundle') and enumerates the payload contents (verdict, profile signals, one-hop relations, receipt stats). This cleanly distinguishes it from siblings like screen_address (single verdict) and deep_trace (graph traversal).

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?

Provides useful operational context — free, 10 per minute, anyone may request — but never states when to prefer this bundle over screen_address, deep_trace, or batch_screen. Usage is implied by the payload description rather than stated as a selection rule.

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