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

With no annotations, the description carries the full burden and does well: it discloses the local-signing model, the return contract {fields, signable}, the required hand-off to `report`, and the key-security guarantee ('the private key never travels'). What it omits is whether `action` (report/block/unblock) changes the returned payload or any prerequisite/authentication requirement.

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?

Three tight sentences, front-loaded with the flow role and immediately followed by the return contract and hand-off. The '[KEEP · internal]' tag is minor meta overhead rather than wasted prose.

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, yet the description specifies the return shape and the next-step contract, which is exactly what an agent needs to chain into `report`. The remaining gap is the undocumented `extra`/`target_id` parameters and unblock behavior.

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 only 50% – `actor` ('your public key') and `action` (report | block | unblock) are documented in the schema, but `extra` and `target_id` are undocumented in both places and the description does not fill that gap. The description adds flow meaning (what to do with `signable`) but not per-parameter semantics.

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+resource: it returns the canonical bytes to sign as step 1 of a report or block, and states the return shape {fields, signable}. It distinguishes its role from the downstream `report` tool, but does not differentiate itself from the sibling signable tools (curate_signable, mesh_signable, playbook_signable, shelf_signable).

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?

Clear sequencing guidance: sign the decoded bytes locally, then pass BOTH fields and signature to `report`. It states when to use it (step 1 of report/block) but gives no explicit exclusion or contrast against the other *_signable siblings, so an agent could still misroute within the signable family.

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