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

With no annotations, the description must carry behavioral burden. It discloses a key constraint ('the key never travels') and entry requirements. However, it doesn't state whether the operation has side effects, requires authentication, or what the output looks like beyond 'bytes'.

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 sentences with no fluff; every sentence adds critical information. The 'Step 1' prefix front-loads context, and security detail is compactly included.

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 14 parameters, no output schema, and no annotations, the description covers only entry-specific constraints. It omits requirements for other ops, expected output format, and workflow integration, making it incomplete for a complex tool.

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 explains `op` and gives detailed requirements for `entry` (confession, anchors, action), but leaves 10 of 14 parameters unexplained (e.g., `by`, `body`, `note`, `outcome`). This partial coverage is insufficient for arbitrary ops like witness or prune.

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 clearly states the tool generates the exact bytes to sign for a Playbook write, with a specific verb ('sign') and resource ('Playbook write'). It distinguishes from siblings like playbook_read (read operation) and other _signable tools by specifying 'Playbook write'.

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?

It explicitly positions itself as 'Step 1' for a Playbook write, implying it should be used before playbook_submit. However, it doesn't explicitly mention alternatives or when not to use it, leaving some guidance implicit.

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