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

Annotations already cover readOnly, idempotent, non-destructive, and closed-world, so the bar is lower. Beyond those, the description adds real behavioral context: empty invocation is valid, no proof is required, and 'Every answer carries the hash recipe so you can recompute it yourself' discloses a return property the agent would not otherwise expect. 'Read-only, no proof' partly restates readOnlyHint, but the added claims are substantive.

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?

Single dense paragraph with no filler; the multi-mode summary is front-loaded and each clause carries new information. The telegraphic phrasing compresses a couple of concepts past the point of immediate clarity, but nothing is wasted.

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?

An output schema exists, so return values need not be spelled out, yet the description still volunteers that answers include the hash recipe. Combined with the three invocation modes and the explicit 'Empty is allowed', an agent has enough to call it correctly without opening the schema. The auth path for leave_token is only hinted at, which is the remaining thin spot.

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% and all seven parameters are documented in the schema, including the sequencing semantics of 'after', the 64-hex constraint on sha256, and the auth behavior of leave_token. The description only loosely gestures at sha256/seq/after and adds no syntax or format detail beyond the schema, so 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?

It states the verb (checks) and resource (stamps) and enumerates the invocation modes: sha256/seq for one receipt, after to walk the chain, or no arguments for the count and head. It also names the sibling it serves, 'verify a stamp_digest receipt', which lets an agent separate it from stamp_digest. The only drag is jargon ('the desk count and head', 'no proof') that is not fully self-explanatory.

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?

The description maps argument combinations to intents (sha256 or seq for one receipt vs. after for the chain vs. empty for the count/head) and states 'Empty is allowed', which is the main non-obvious usage question for a 0-required-param tool. It provides no explicit when-not or competing-alternative guidance, so it stops short of a 5.

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