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

Annotations declare readOnlyHint=true and destructiveHint=false, but the description's core claim — a 'hash-chained ... notary' for 'audit trails' — implies appending a persistent, chained attestation record, i.e., a state-changing write. Beyond that conflict, the description says nothing about side effects, whether attestations are immutable or idempotent, or what proof the caller receives back, which for a notary tool is the single most important behavioral fact.

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?

It is a single tight sentence with no filler, and the defining concept is front-loaded. The cost is density of jargon ('tamper-evident', 'hash-chained', 'Notary') packed into one clause rather than a clear statement of action.

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 four-parameter tool with no output schema, the description should say what an attestation call returns (a chain hash, an attestation id, a receipt) and when one must be created. Instead it supplies branding, leaving both the return contract and the operational trigger unstated.

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 descriptions of summary, agent_id, action_type, and payload_sha256 already carry the parameter semantics. The tool description adds nothing about any of them (e.g., whether payload_sha256 is expected for high-risk actions or how action_type is used in the chain), 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?

The description is a noun-phrase marketing label ('Tamper-evident SHA-256 hash-chained Agent Decision & Compliance Notary') that expands the tool name rather than stating a verb+resource action. It does convey the domain (compliance attestation of agent decisions) and names three frameworks, so an agent can guess the intent, but it never says plainly 'records an attestation entry'. Sibling tools are all unrelated data-lookup tools, so differentiation is not the issue; the ambiguity is in what the tool actually performs.

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?

There is no when-to-use guidance at all: no conditions under which an agent should attest a decision, no prerequisites, and no mention of alternatives or follow-up steps. It is not misleading, but every routing decision is left to inference from the tool name alone.

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