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

With no annotations provided, the description carries the full burden and does disclose meaningful behavior: entries start in QUARANTINE and reach CONFIRMED only via TWO independent witnesses (author excluded), a wait must elapse, outcomes are recorded after the fact, and failed fruit may be PRUNED with 'Failure is not hidden'. This state-machine context is genuinely valuable, though permission/auth requirements and return behavior are unstated.

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 action is front-loaded, which is good, but the '[KEEP · internal]' prefix is meta-noise and the biblical citations (Deut 19:15, John 15:2) add flavor rather than operational value. The sentences are dense with jargon that costs comprehension.

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 complex tool (4 params, a nested `fields` object with additionalProperties:false and no defined properties, no output schema, no annotations), the description is incomplete. It never says what `fields` must contain or what 'those exact bytes' refers to, so an agent cannot reliably construct a correct call.

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 0%, so the description must compensate. It effectively explains all four `op` enum values conceptually (entry, witness/affirm, outcome, prune), which adds real meaning over the bare enum, but the `fields` object, `signature`, and `display_name` parameters are never described, leaving gaps the schema cannot fill.

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?

The description conveys a verb+resource (verify a detached signature and enter a testimony/event into the playbook), but it is wrapped in heavy metaphorical jargon ('born QUARANTINE', 'brothers affirm', 'fruit'). It never names the sibling tools (playbook_signable, playbook_read) or cleanly states the operation, so an agent must decode the prose to grasp the purpose.

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?

'Step 2 — verify your detached signature over those exact bytes' implies this follows the signing step, and the lifecycle prose hints when outcome/prune are used ('later, after it is seen'). However, there is no explicit when-to-use guidance for the four ops and no named alternative, leaving routing to inference.

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