create_evidence_pack

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

With annotations already declaring readOnlyHint=false, destructiveHint=false and idempotentHint=false, the description adds real context: it hashes rather than mutates, produces an immutable artifact, and discloses the return shape. It does not address the non-idempotent implication (repeat calls yielding distinct packs), which is the one behavioral gap left to annotations.

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 core purpose and return shape are front-loaded and the text is dense with little waste. The final sentence restates 'immutable cryptographic' and repeats the tool's own name, which is slight redundancy but it carries the sibling differentiation.

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?

No output schema exists, but the description supplies the return shape ({ok, pack_id, hash, payload}), which covers the main informational gap. For a 7-parameter, nested-object, zero-required tool it is nearly complete, though it never explains what happens when the optional ID sets are omitted.

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 the schema already documents all seven parameters, including the nested linked_state_memory_nodes object. The description maps its prose ('entity positions, observation reconciliations, snapshot states') onto some of those inputs but adds no format, ordering, or requiredness guidance beyond the schema.

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?

Specific verb ('package') plus named resources (entity positions, observation reconciliations, snapshot states) and a declared output artifact (immutable SHA-256 hashed evidence pack). It also distinguishes itself from the sibling manage_snapshot by scope, so an agent can separate the two without opening either 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?

Explicitly states the selection rule against an alternative: use this instead of manage_snapshot when producing immutable cryptographic verification packages rather than database checkpoints. It also clarifies the non-mutation boundary ('does not change entities; hashes current proof').

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