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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safety profile is covered. The description adds value beyond annotations by disclosing data semantics: 'The city does not rewrite Hold history' tells the agent the underlying records are immutable, which affects how results should be interpreted. 'Read only' is redundant with the annotations, but not contradictory.

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 description is four terse fragments — endpoint, purpose, safety, and a key behavioral trait about immutability — with no wasted words. The most identifying information ('GET /api/hold. Vault listing.') is front-loaded, and every sentence earns its place.

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 an output schema present, return values need not be explained, and the annotation set covers the read-only/idempotent/non-destructive profile. The description communicates purpose and the key immutability trait. The main gap is usage context: an agent navigating many sibling tools (hold_receipt, seal_history, passport_history) gets no guidance on when this listing is the right choice.

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 all four parameters (nonce, leave_token, controller_signature, controller_public_key) are already fully documented in the input schema. The tool description itself contains no parameter information, but the baseline of 3 applies because the schema carries the explanatory burden, including security-sensitive notes about the leave_token.

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 names a specific verb and resource ('GET /api/hold') and characterizes it as a 'Vault listing. Read only.' This is clear about what the tool does. However, it does not explicitly differentiate itself from the sibling hold_receipt or from listing tools like seal_history and passport_history, so an agent must infer the distinction.

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 statement of when to use this tool versus alternatives such as hold_receipt or seal_history. The phrase 'The city does not rewrite Hold history' implies the trail is immutable, but it does not tell an agent when to select this tool or when to use a sibling. No exclusions or alternative routing are provided.

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